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

    Neuronpedia

    INDEX
    Explanations

    section headers or keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urization
    0.72
    alui
    0.70
     vgl
    0.66
    理論
    0.65
    endlich
    0.64
    surprisingly
    0.64
    #######
    0.64
    introduction
    0.63
     introduction
    0.63
    eşit
    0.63
    POSITIVE LOGITS
     Warning
    0.97
     Sign
    0.91
     Warnings
    0.87
     Plain
    0.86
     News
    0.85
     Highlights
    0.85
     Advert
    0.84
     Signs
    0.80
     Instructions
    0.79
     Specials
    0.77
    Act Density 0.003%

    No Known Activations