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

    Neuronpedia

    INDEX
    Explanations

    to/into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thai
    -0.08
     subordinate
    -0.08
     Bou
    -0.07
     circus
    -0.07
     Mediterranean
    -0.07
     temporary
    -0.07
     sayısı
    -0.07
     sublist
    -0.07
     mM
    -0.07
     respondent
    -0.07
    POSITIVE LOGITS
    iting
    0.07
    _CHAT
    0.07
    lined
    0.07
    htub
    0.06
    /")
    0.06
    يب
    0.06
    _layer
    0.06
    (logging
    0.06
     insights
    0.06
     Ally
    0.06
    Act Density 0.018%

    No Known Activations