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

    Neuronpedia

    INDEX
    Explanations

    _source

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    εχ
    -0.06
     úč
    -0.06
     psz
    -0.06
     yorum
    -0.06
    jspb
    -0.06
     rall
    -0.05
    rop
    -0.05
     drafting
    -0.05
     بالق
    -0.05
    非
    -0.05
    POSITIVE LOGITS
    .bel
    0.08
     इतन
    0.08
     Norse
    0.07
    真是
    0.07
    ========↵
    0.07
    .Output
    0.07
    isex
    0.07
    caught
    0.06
     insensitive
    0.06
    _^
    0.06
    Act Density 0.001%

    No Known Activations