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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inski
    -0.06
    liš
    -0.06
     زیست
    -0.06
     geld
    -0.06
     lu
    -0.06
    684
    -0.06
     dosud
    -0.06
    Query
    -0.06
     hari
    -0.06
     day
    -0.06
    POSITIVE LOGITS
     [["
    0.07
    那些
    0.07
    _FRONT
    0.07
    .parametrize
    0.07
    Truthy
    0.07
    協
    0.07
    assadors
    0.07
    JO
    0.06
    Coffee
    0.06
     FontAwesome
    0.06
    Act Density 0.073%

    No Known Activations