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

    Neuronpedia

    INDEX
    Explanations

    analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salv
    -0.07
     něco
    -0.07
    vangst
    -0.07
    属
    -0.06
     athe
    -0.06
     filtro
    -0.06
     clas
    -0.06
     acción
    -0.06
     disc
    -0.06
    ันน
    -0.06
    POSITIVE LOGITS
     architectures
    0.06
    �
    0.06
    RECT
    0.06
    app
    0.06
     Lets
    0.06
    _ranges
    0.06
    гу
    0.06
    рою
    0.06
    _PAYLOAD
    0.06
    We
    0.06
    Act Density 0.069%

    No Known Activations