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

    Neuronpedia

    INDEX
    Explanations

    references to programming environments and error handling

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

    installing or choosing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.60
     '\\;'
    -0.57
    ::_('
    -0.52
     الحره
    -0.52
    RegressionTest
    -0.50
     Wicidata
    -0.49
    -0.48
     ActiveRecord
    -0.47
    OGND
    -0.46
    Hentet
    -0.46
    POSITIVE LOGITS
     installed
    0.43
     installing
    0.43
     install
    0.42
     instalar
    0.42
    alamualaikum
    0.41
     installation
    0.40
    install
    0.38
     Kop
    0.38
     initialState
    0.38
    Installing
    0.38
    Act Density 0.129%

    No Known Activations