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

    Neuronpedia

    INDEX
    Explanations

    program termination/cleanup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    混合
    -0.06
     Ank
    -0.06
    然后
    -0.06
     �
    -0.06
    _PRE
    -0.06
    Cross
    -0.05
    ським
    -0.05
     válido
    -0.05
     câ
    -0.05
    Это
    -0.05
    POSITIVE LOGITS
    .cleaned
    0.07
    alo
    0.07
    svp
    0.07
    ushed
    0.07
    erg
    0.07
     صور
    0.06
    ast
    0.06
     University
    0.06
    <pre
    0.06
    ’:
    0.06
    Act Density 0.001%

    No Known Activations