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

    Neuronpedia

    INDEX
    Explanations

    localization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    requencies
    -0.07
    _open
    -0.07
     holes
    -0.06
    ：</
    -0.06
    rowsing
    -0.06
    .item
    -0.06
     READY
    -0.06
    feit
    -0.06
     Principle
    -0.06
     інформа
    -0.06
    POSITIVE LOGITS
     smart
    0.07
     сол
    0.07
    مج
    0.07
    농
    0.06
    Little
    0.06
    �
    0.06
    竞
    0.06
     dangerous
    0.06
     Veter
    0.06
    .mult
    0.06
    Act Density 0.003%

    No Known Activations