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

    Neuronpedia

    INDEX
    Explanations

    clarifying what something isn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ため
    1.26
    Sports
    1.24
    还
    1.23
    マ
    1.20
    ного
    1.14
    新
    1.12
    ंछ
    1.12
    没有
    1.12
    な
    1.12
    ihkan
    1.12
    POSITIVE LOGITS
     repeatable
    1.13
    ுங்கள்
    1.12
     ∆
    1.09
     finalText
    1.05
     fuese
    1.02
     effluents
    1.01
     tessel
    0.99
     surging
    0.99
     poised
    0.97
     invent
    0.97
    Act Density 0.001%

    No Known Activations