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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    হ
    1.53
    RE
    1.41
    其
    1.38
    ह
    1.36
    AR
    1.34
    G
    1.34
    ats
    1.30
    રો
    1.30
    A
    1.28
    HAM
    1.27
    POSITIVE LOGITS
    ている
    1.37
     uproar
    1.23
    ➙
    1.22
     hogar
    1.21
    s
    1.20
     menace
    1.19
     ejecut
    1.19
    clamation
    1.17
     estrict
    1.17
    て
    1.13
    Act Density 0.103%

    No Known Activations