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

    Neuronpedia

    INDEX
    Explanations

    YS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     popis
    -0.07
    레
    -0.07
     YE
    -0.07
     forfe
    -0.06
     Sacr
    -0.06
     نیاز
    -0.06
    ListOf
    -0.06
    uploader
    -0.06
    вид
    -0.06
    ायन
    -0.06
    POSITIVE LOGITS
    (EFFECT
    0.08
     ilgi
    0.06
     turtle
    0.06
    Impl
    0.06
    _v
    0.06
     Virginia
    0.06
    서는
    0.06
     front
    0.06
    enko
    0.06
     resonance
    0.06
    Act Density 0.005%

    No Known Activations