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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fah
    -0.07
    锛
    -0.07
     Bedford
    -0.06
    .visitMethodInsn
    -0.06
     المشاركة
    -0.06
     Edward
    -0.06
    .NotFound
    -0.06
    哈佛
    -0.06
    -disc
    -0.06
     zones
    -0.06
    POSITIVE LOGITS
     contenders
    0.07
     interes
    0.07
    금
    0.06
    どころ
    0.06
    ILER
    0.06
     natur
    0.06
     inne
    0.06
    润滑油
    0.06
    (entry
    0.06
    _warning
    0.06
    Act Density 0.003%

    No Known Activations