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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    io
    -0.07
    ЕР
    -0.07
    OURS
    -0.06
    рос
    -0.06
    ��
    -0.06
    ALLOW
    -0.06
    elijk
    -0.06
    ASF
    -0.06
     NES
    -0.06
    PLIER
    -0.06
    POSITIVE LOGITS
    _performance
    0.07
     getObject
    0.07
     vốn
    0.06
    _NODE
    0.06
     immoral
    0.06
     strategist
    0.06
     Euras
    0.06
     gezocht
    0.06
     çıkart
    0.06
     prolong
    0.06
    Act Density 0.012%

    No Known Activations