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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    İTESİ
    -0.07
    $PostalCodesNL
    -0.06
     AIS
    -0.06
    $category
    -0.06
     Công
    -0.06
     Interaction
    -0.06
     smiled
    -0.06
     keyst
    -0.06
    commission
    -0.06
     motivated
    -0.06
    POSITIVE LOGITS
    /profile
    0.10
    (numpy
    0.08
    VILLE
    0.07
     pathMatch
    0.07
    umba
    0.06
     Hollow
    0.06
    !',↵
    0.06
     NSF
    0.06
    (Stack
    0.06
    (Global
    0.06
    Act Density 0.003%

    No Known Activations