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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sz
    -0.07
    lbs
    -0.07
    ivirus
    -0.07
    晒
    -0.07
    gregator
    -0.06
     creo
    -0.06
    sty
    -0.06
    ﺋ
    -0.06
    UID
    -0.06
    ガイ
    -0.06
    POSITIVE LOGITS
    ═
    0.07
     doll
    0.07
    _health
    0.07
    ponses
    0.07
    .strictEqual
    0.07
    管线
    0.07
     crumbs
    0.07
     MADE
    0.07
     đáo
    0.07
    _commit
    0.07
    Act Density 0.005%

    No Known Activations