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

    Neuronpedia

    INDEX
    Explanations

    say "v" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	txt
    -0.07
    iculo
    -0.06
    SO
    -0.06
     انرژی
    -0.06
    札
    -0.06
    "><?=
    -0.06
    ，说
    -0.06
    .style
    -0.06
    SED
    -0.06
     Zap
    -0.06
    POSITIVE LOGITS
    quier
    0.08
    �
    0.07
     cached
    0.07
     localtime
    0.07
     RequestOptions
    0.06
    _distribution
    0.06
     Extensions
    0.06
     vacation
    0.06
    共和国
    0.06
    .training
    0.06
    Act Density 0.006%

    No Known Activations