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

    Neuronpedia

    INDEX
    Explanations

    Mathematical symbols and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,y
    -0.08
    HK
    -0.07
     conductivity
    -0.07
     Nicol
    -0.06
     horns
    -0.06
    Boom
    -0.06
     Pang
    -0.06
    oma
    -0.06
     çocu
    -0.06
    .Results
    -0.06
    POSITIVE LOGITS
     العل
    0.07
    ــ
    0.07
    θν
    0.07
    _MetaData
    0.06
     الجم
    0.06
    rios
    0.06
    ']↵↵↵
    0.06
     ارز
    0.06
     getters
    0.06
    _JS
    0.06
    Act Density 0.015%

    No Known Activations