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

    Neuronpedia

    INDEX
    Explanations

    instances and examples within the text

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

    introduces examples or instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.46
     memakan
    -0.45
     erw
    -0.45
     slutt
    -0.44
     trekken
    -0.43
     asupra
    -0.43
    illets
    -0.41
     iprot
    -0.40
     menyenangkan
    -0.40
     Ordnung
    -0.40
    POSITIVE LOGITS
    UserScript
    0.57
    UnusedPrivate
    0.56
    parsedMessage
    0.53
    fromnode
    0.51
     informée
    0.49
    LookAnd
    0.49
    IntoConstraints
    0.47
    Dabei
    0.46
    AnchorTagHelper
    0.46
    clusal
    0.45
    Act Density 0.111%

    No Known Activations