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

    Neuronpedia

    INDEX
    Explanations

    section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ABSTRACT
    0.89
     Abstract
    0.86
     abstract
    0.85
    Abstract
    0.77
    abstract
    0.75
     abstracts
    0.75
     абстра
    0.73
     abstr
    0.70
    ABSTRACT
    0.69
     abstra
    0.66
    POSITIVE LOGITS
     opening
    0.46
     åp
    0.45
    เปิด
    0.43
    Opening
    0.43
     opened
    0.41
     membuka
    0.40
    дії
    0.40
    opening
    0.40
    lik
    0.39
    opened
    0.38
    Act Density 0.000%

    No Known Activations