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

    Neuronpedia

    INDEX
    Explanations

    housing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     partir
    -0.07
    mention
    -0.07
    なければ
    -0.07
    options
    -0.06
     않았다
    -0.06
    %.
    -0.06
     Thursday
    -0.06
     Sunday
    -0.06
    _ch
    -0.06
    MinMax
    -0.06
    POSITIVE LOGITS
     envi
    0.07
    yers
    0.07
     Tracy
    0.07
    .toast
    0.07
     основе
    0.06
    /dr
    0.06
    097
    0.06
    ulia
    0.06
    �
    0.06
     victims
    0.06
    Act Density 0.024%

    No Known Activations