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

    Neuronpedia

    INDEX
    Explanations

    труд

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    之美
    -0.07
    /settings
    -0.07
    .Nome
    -0.06
    褚
    -0.06
    说的话
    -0.06
     palabras
    -0.06
    _DIRECTION
    -0.06
    �
    -0.06
    dsl
    -0.06
     Verizon
    -0.06
    POSITIVE LOGITS
     perpetr
    0.07
    obao
    0.07
    untary
    0.07
    aar
    0.06
     zes
    0.06
    ]])↵↵
    0.06
    خب
    0.06
    かり
    0.06
    .Decimal
    0.06
    讓他們
    0.06
    Act Density 0.005%

    No Known Activations