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

    Neuronpedia

    INDEX
    Explanations

    code as a creative text format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ponses
    0.43
    ӵ
    0.39
     décou
    0.39
    ailed
    0.39
     bureaucracy
    0.38
    affes
    0.38
    alui
    0.37
     sabbam
    0.37
     afiliados
    0.37
     BCC
    0.37
    POSITIVE LOGITS
    computer
    0.39
    煥
    0.39
     Tide
    0.37
    COMPUTER
    0.37
     Entertain
    0.37
     computer
    0.36
     Computing
    0.35
    ద్దు
    0.35
     odds
    0.35
     Odds
    0.35
    Act Density 0.003%

    No Known Activations