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

    Neuronpedia

    INDEX
    Explanations

    pm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    心跳
    -0.08
     courts
    -0.08
    𫑡
    -0.08
     מצווה
    -0.07
     منت
    -0.07
    .bb
    -0.07
     hazard
    -0.06
    hq
    -0.06
    쭘
    -0.06
    .readLine
    -0.06
    POSITIVE LOGITS
    	th
    0.07
    jiang
    0.07
    로그
    0.07
    	Item
    0.07
    ources
    0.07
    lg
    0.07
    есп
    0.07
    Israeli
    0.07
    ⽐
    0.07
    夕阳
    0.06
    Act Density 0.011%

    No Known Activations