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

    Neuronpedia

    INDEX
    Explanations

    touch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    漫
    -0.08
    烈
    -0.08
    汗
    -0.07
     rocket
    -0.07
    (Table
    -0.07
     Clan
    -0.07
    .sol
    -0.07
    ILog
    -0.07
     ws
    -0.07
     para
    -0.07
    POSITIVE LOGITS
     touching
    0.08
     respectively
    0.07
    _COMPLEX
    0.07
    touches
    0.07
    feas
    0.07
    quence
    0.07
    rm
    0.07
     особенно
    0.06
    差别
    0.06
     assumption
    0.06
    Act Density 0.025%

    No Known Activations