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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENDIF
    -0.06
    (year
    -0.06
    .Dispatch
    -0.06
     nombreux
    -0.06
    _KHR
    -0.06
     Heard
    -0.06
     newcomer
    -0.06
    equip
    -0.06
    \model
    -0.06
    Њ
    -0.06
    POSITIVE LOGITS
    клад
    0.07
     xe
    0.07
     mile
    0.07
    getSource
    0.06
    Cube
    0.06
     attach
    0.06
    //=
    0.06
    Bur
    0.06
     op
    0.06
     книж
    0.06
    Act Density 0.001%

    No Known Activations