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

    Neuronpedia

    INDEX
    Explanations

    large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eis
    0.70
    Prompt
    0.70
    prompt
    0.68
     Kw
    0.67
     공식
    0.67
     Lemon
    0.66
     Bonner
    0.66
     Eis
    0.66
     annotate
    0.66
     Gins
    0.65
    POSITIVE LOGITS
    Large
    1.35
     Large
    1.33
     large
    1.29
    large
    1.14
     LARGE
    1.11
     larges
    0.93
     language
    0.90
     বৃহৎ
    0.87
     большим
    0.85
     grandi
    0.83
    Act Density 0.164%

    No Known Activations