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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     processes
    -0.08
    Probe
    -0.07
     miệ
    -0.07
     seemed
    -0.07
     Liquid
    -0.07
    業務
    -0.07
    Perm
    -0.07
    无
    -0.07
    fläche
    -0.07
    ﴘ
    -0.07
    POSITIVE LOGITS
     Swap
    0.07
    autiful
    0.07
    高贵
    0.07
    老实
    0.07
    ('/')[-
    0.06
    (offset
    0.06
     awkward
    0.06
    烟台
    0.06
    .TextField
    0.06
    跛
    0.06
    Act Density 0.091%

    No Known Activations