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

    Neuronpedia

    INDEX
    Explanations

    discussions and statements about strategic decisions and their implications

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

    discussing and highlighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.45
    multer
    -0.42
    ミナル
    -0.41
     humains
    -0.39
     bacteria
    -0.39
     Reader
    -0.39
     blade
    -0.39
    bibfield
    -0.38
    endpush
    -0.38
     reader
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.52
    verifyException
    0.51
    AndEndTag
    0.50
    IntoConstraints
    0.50
     <<<<<<<<<<<<<<
    0.50
     discussed
    0.49
    InitStruct
    0.49
    writeFieldEnd
    0.49
    BagConstraints
    0.48
    ⓧ
    0.48
    Act Density 0.007%

    No Known Activations