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

    Neuronpedia

    INDEX
    Explanations

    say "-" sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    especially
    -0.11
    ...↵↵
    -0.10
    …↵↵
    -0.10
    .↵↵
    -0.10
    ------↵↵
    -0.09
    Also
    -0.09
     especially
    -0.09
    ----↵↵
    -0.09
    ’s
    -0.09
    particularly
    -0.09
    POSITIVE LOGITS
     Wrapped
    0.09
    .Classes
    0.09
     Sticky
    0.09
     স্থানীয়
    0.08
     Ciudad
    0.08
     Situated
    0.08
     Nested
    0.08
     સ્થાનિક
    0.08
     ҳақ
    0.08
     анҷ
    0.08
    Act Density 0.076%

    No Known Activations