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

    Neuronpedia

    INDEX
    Explanations

    fluence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     승
    -0.07
     Decomp
    -0.07
    .decoder
    -0.07
    phins
    -0.06
    (`
    -0.06
     kararı
    -0.06
     kişisel
    -0.06
     yüz
    -0.06
    _cash
    -0.06
     quarterback
    -0.06
    POSITIVE LOGITS
     Influence
    0.12
     influence
    0.11
    fluence
    0.11
     geliş
    0.07
     پیدا
    0.07
    cmath
    0.06
    /maps
    0.06
    Opera
    0.06
    /render
    0.06
     love
    0.06
    Act Density 0.005%

    No Known Activations