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
    _WE
    -0.08
     buds
    -0.07
    rar
    -0.06
    .legend
    -0.06
     listar
    -0.06
    डर
    -0.06
     provoc
    -0.06
    _Object
    -0.06
     Pazar
    -0.06
    .Manager
    -0.06
    POSITIVE LOGITS
     interpre
    0.07
    birthday
    0.06
    096
    0.06
     Instruments
    0.06
    _generation
    0.06
     afterwards
    0.06
    陷
    0.06
    olet
    0.06
     commissions
    0.06
     aday
    0.06
    Act Density 0.000%

    No Known Activations