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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ode
    -0.07
    dots
    -0.07
     nú
    -0.06
    be
    -0.06
     governor
    -0.06
     SEN
    -0.06
    Source
    -0.06
     Specs
    -0.06
    (dr
    -0.06
    ime
    -0.06
    POSITIVE LOGITS
     Franklin
    0.08
     reconstruct
    0.08
    ifacts
    0.08
    氢
    0.07
    瘫
    0.07
    传统文化
    0.07
    ￂ
    0.07
    _iff
    0.07
     toured
    0.06
     конструк
    0.06
    Act Density 0.003%

    No Known Activations