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

    Neuronpedia

    INDEX
    Explanations

    despite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     killings
    -0.07
    imuth
    -0.06
     CONTRIBUT
    -0.06
    _Com
    -0.06
    契
    -0.06
    inging
    -0.06
     hostname
    -0.06
    bz
    -0.06
     Compilation
    -0.06
    (stage
    -0.06
    POSITIVE LOGITS
    ैश
    0.07
    familia
    0.06
    offee
    0.06
    .Throws
    0.06
     Rated
    0.06
    liked
    0.06
    apixel
    0.06
     شعر
    0.06
     Despite
    0.06
     tiers
    0.06
    Act Density 0.010%

    No Known Activations