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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detecting
    -0.06
    Letters
    -0.06
     DVDs
    -0.06
    紙
    -0.06
    елей
    -0.06
    查询
    -0.05
     reporter
    -0.05
     查询
    -0.05
     Opport
    -0.05
     juin
    -0.05
    POSITIVE LOGITS
     wchar
    0.07
    NSIndexPath
    0.07
     desar
    0.06
    _constraints
    0.06
     přest
    0.06
    _pd
    0.06
     نص
    0.06
    ackers
    0.06
    _transfer
    0.06
    ***↵
    0.06
    Act Density 0.000%

    No Known Activations