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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    months
    0.50
    month
    0.47
    infested
    0.46
    liy
    0.45
    კ
    0.45
    مت
    0.44
    مي
    0.43
    l
    0.43
    infected
    0.43
    เจ
    0.42
    POSITIVE LOGITS
     Promoter
    0.48
     HCl
    0.47
    esco
    0.47
     Genomics
    0.47
     wikiHow
    0.46
     Molecular
    0.46
     Ayurved
    0.46
    ogenetics
    0.45
    ྒྱ
    0.45
     Finger
    0.45
    Act Density 0.003%

    No Known Activations