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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     самый
    -0.07
     victory
    -0.07
     template
    -0.07
     sle
    -0.07
     Claudia
    -0.07
     fout
    -0.06
    找到
    -0.06
    典
    -0.06
     نقش
    -0.06
    #/
    -0.06
    POSITIVE LOGITS
    机关
    0.07
    忽
    0.06
    mac
    0.06
     않
    0.06
    _mv
    0.06
    combine
    0.06
     pivot
    0.06
    getBlock
    0.06
     Indicates
    0.06
     RT
    0.06
    Act Density 0.116%

    No Known Activations