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
    🎞
    -0.07
    więt
    -0.07
    lesai
    -0.07
    gf
    -0.07
    IZER
    -0.07
     עסק
    -0.06
    纵向
    -0.06
    采纳
    -0.06
    _("
    -0.06
     בחשבון
    -0.06
    POSITIVE LOGITS
    (play
    0.07
    NE
    0.07
    hon
    0.07
    ANTI
    0.06
     Score
    0.06
    โบ
    0.06
    Backing
    0.06
    update
    0.06
     있는데
    0.06
    _PA
    0.06
    Act Density 0.000%

    No Known Activations