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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    docs
    -0.07
    _override
    -0.07
    _should
    -0.06
    _recovery
    -0.06
    _projection
    -0.06
     fontFamily
    -0.06
     мов
    -0.06
    En
    -0.06
     Minimum
    -0.06
    -fix
    -0.06
    POSITIVE LOGITS
    /helper
    0.07
     Neck
    0.06
    IBUTE
    0.06
    osed
    0.06
    rador
    0.06
     Divine
    0.06
    ome
    0.06
     глу
    0.06
     Mans
    0.06
    VERTISE
    0.06
    Act Density 0.044%

    No Known Activations