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

    Neuronpedia

    INDEX
    Explanations

    training time for models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.75
    m
    0.74
    b
    0.73
    िख
    0.70
    conscious
    0.65
    म
    0.62
    r
    0.61
    м
    0.61
    蔦
    0.60
    t
    0.59
    POSITIVE LOGITS
     Diakses
    0.92
     macromolecules
    0.88
     आफ्नो
    0.88
     invertebr
    0.86
     desenvolver
    0.85
     ケース
    0.85
    ্বাদ
    0.85
     थी
    0.85
     Deshalb
    0.84
     micelles
    0.83
    Act Density 0.001%

    No Known Activations