Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their associated actions or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding reported speech or thought

    np_acts-logits-general · gemini-2.0-flash

    what is said or expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toggler
    -0.50
    FormTagHelper
    -0.49
    HasForeignKey
    -0.49
     Cuckoo
    -0.49
    ژاد
    -0.47
     consultato
    -0.46
    @",
    -0.45
    arischen
    -0.44
     farlo
    -0.44
    berdayakan
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.84
     happening
    0.69
     EconPapers
    0.68
    thâu
    0.65
     accomplished
    0.62
    IntoConstraints
    0.62
    GOTREF
    0.61
     eat
    0.61
    UnitTesting
    0.61
     done
    0.60
    Act Density 0.143%

    No Known Activations