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

    Neuronpedia

    INDEX
    Explanations

    Non-standard English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stag
    -0.07
     Marxist
    -0.07
    itamin
    -0.06
     Materials
    -0.06
    下
    -0.06
     Kop
    -0.06
     Mini
    -0.06
    /loading
    -0.06
    amping
    -0.06
     Changes
    -0.06
    POSITIVE LOGITS
    ATHER
    0.07
    .pg
    0.07
    रत
    0.06
     Abbas
    0.06
     Aralık
    0.06
     incarcer
    0.06
     echt
    0.06
    orda
    0.06
    Cómo
    0.06
    骑
    0.06
    Act Density 0.019%

    No Known Activations