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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ━━━━
    -0.07
    rnd
    -0.07
    Beyond
    -0.07
    说
    -0.07
    ещ
    -0.06
     рассказ
    -0.06
     catches
    -0.06
     Supports
    -0.06
    _word
    -0.06
     rhyme
    -0.06
    POSITIVE LOGITS
    serrat
    0.06
     Oven
    0.06
     PropertyChanged
    0.06
     wb
    0.06
     맡
    0.06
    Signals
    0.06
    ixmap
    0.06
    Perl
    0.06
    */
↵
    0.06
     redux
    0.06
    Act Density 0.080%

    No Known Activations