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

    Neuronpedia

    INDEX
    Explanations

    chastity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungan
    -0.08
     Griffin
    -0.08
     Roulette
    -0.07
     Interior
    -0.07
     meltdown
    -0.06
     Ford
    -0.06
    inactive
    -0.06
     LJ
    -0.06
     目
    -0.06
     Plugin
    -0.06
    POSITIVE LOGITS
    >

↵
    0.06
    .just
    0.06
    ipt
    0.06
    يث
    0.06
    _Collections
    0.06
     ere
    0.06
     sólo
    0.06
    τών
    0.06
    pac
    0.06
    yt
    0.06
    Act Density 0.001%

    No Known Activations