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

    Neuronpedia

    INDEX
    Explanations

    F-word and machine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cluster
    -0.07
    _employee
    -0.06
    .pref
    -0.06
    aways
    -0.06
    _loan
    -0.06
     tribe
    -0.06
    ्रक
    -0.06
    wich
    -0.06
     сер
    -0.06
     Sistem
    -0.06
    POSITIVE LOGITS
    (Android
    0.07
    POSITION
    0.07
     oxy
    0.06
    _pix
    0.06
    onis
    0.06
     acceptance
    0.06
     medically
    0.06
     Andres
    0.06
    ILITY
    0.06
    WIDTH
    0.06
    Act Density 0.005%

    No Known Activations