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

    Neuronpedia

    INDEX
    Explanations

    reign of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    á
    1.62
    턴
    1.60
    rs
    1.47
     वही
    1.47
    ă
    1.39
    ง
    1.38
    urious
    1.35
    g
    1.35
    ó
    1.34
     berwarna
    1.33
    POSITIVE LOGITS
    />}/>
    1.84
    ྜ
    1.70
    ی
    1.69
     animaux
    1.54
     capito
    1.46
    ار
    1.45
     разработки
    1.44
     deities
    1.43
     cosidd
    1.42
    ل
    1.42
    Act Density 0.001%

    No Known Activations