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

    Neuronpedia

    INDEX
    Explanations

    gate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nero
    -0.07
     فتح
    -0.07
     filmes
    -0.06
    .conv
    -0.06
     rew
    -0.06
    초
    -0.06
     mesmer
    -0.06
    oš
    -0.06
    egot
    -0.06
    ijn
    -0.06
    POSITIVE LOGITS
    体
    0.06
    .mContext
    0.06
     Ban
    0.06
    SQLException
    0.06
    cej
    0.06
     hakkında
    0.06
     Recommendation
    0.06
    ujet
    0.06
    begin
    0.06
    map
    0.06
    Act Density 0.002%

    No Known Activations