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

    Neuronpedia

    INDEX
    Explanations

    About

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    players
    -0.07
    :${
    -0.07
     které
    -0.06
     borrowers
    -0.06
    (*(
    -0.06
    inions
    -0.06
     Ferd
    -0.06
    (((
    -0.06
     læ
    -0.06
     agreements
    -0.06
    POSITIVE LOGITS
    _UnityEngine
    0.07
    _likelihood
    0.07
    archives
    0.06
     حالت
    0.06
    .Highlight
    0.06
     relaciones
    0.06
     scalar
    0.06
    DE
    0.06
    madığı
    0.06
    CASE
    0.06
    Act Density 0.003%

    No Known Activations