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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ollision
    -0.07
     виду
    -0.07
     Tracking
    -0.06
     cinemas
    -0.06
    ..↵↵
    -0.06
    quiry
    -0.06
     Impro
    -0.06
     letz
    -0.06
     Generic
    -0.06
    gtk
    -0.06
    POSITIVE LOGITS
    _FUNC
    0.06
    sten
    0.06
     Heather
    0.06
    ances
    0.06
    ações
    0.06
    (dx
    0.06
    IBC
    0.06
    281
    0.06
    crud
    0.06
    ance
    0.06
    Act Density 0.031%

    No Known Activations