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

    Neuronpedia

    INDEX
    Explanations

    program director

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    1.17
    .
    0.96
     மற்றும்
    0.95
     및
    0.89
    /
    0.86
     structures
    0.84
     ਅਤੇ
    0.84
     systems
    0.83
     एवं
    0.83
     of
    0.81
    POSITIVE LOGITS
    بعض
    0.95
    ယောက်
    0.89
     childish
    0.83
    最初の
    0.82
    自分の
    0.78
     కొన్ని
    0.78
    簡単な
    0.78
     pouquinho
    0.76
    awsze
    0.76
     कुछ
    0.75
    Act Density 0.000%

    No Known Activations