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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostitu
    -0.07
    iration
    -0.06
     adopt
    -0.06
    /P
    -0.06
    _seek
    -0.06
    rypted
    -0.06
    ("""
    -0.06
    (HttpStatus
    -0.06
    \Desktop
    -0.06
     accidents
    -0.06
    POSITIVE LOGITS
    cess
    0.07
     difer
    0.07
    _ment
    0.06
    :name
    0.06
    iceps
    0.06
    мы
    0.06
     مختلف
    0.06
     automat
    0.06
    oucí
    0.06
     temporada
    0.06
    Act Density 0.003%

    No Known Activations