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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nvarchar
    -0.08
    778
    -0.07
     granny
    -0.07
     spectrum
    -0.06
     SEX
    -0.06
     explanation
    -0.06
    _exec
    -0.06
    .asm
    -0.06
    Explanation
    -0.06
     terr
    -0.06
    POSITIVE LOGITS
    igar
    0.07
    .toList
    0.07
     fundraising
    0.06
     разі
    0.06
     고
    0.06
    ѓ
    0.06
     ذکر
    0.05
    기로
    0.05
    /change
    0.05
     traitement
    0.05
    Act Density 0.016%

    No Known Activations