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

    Neuronpedia

    INDEX
    Explanations

    psych

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ırı
    -0.08
     XII
    -0.07
     slope
    -0.06
    flat
    -0.06
    _o
    -0.06
    _SURFACE
    -0.06
     Bayesian
    -0.06
    .swt
    -0.06
    �
    -0.06
    -negative
    -0.06
    POSITIVE LOGITS
    ucs
    0.07
     SC
    0.07
    anyahu
    0.07
     post
    0.07
    ADS
    0.07
     searcher
    0.06
    SF
    0.06
     Fortnite
    0.06
    FB
    0.06
     Lik
    0.06
    Act Density 0.005%

    No Known Activations