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

    Neuronpedia

    INDEX
    Explanations

    reporting verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    1.27
    च्या
    1.24
    ची
    1.20
     these
    1.16
     takich
    1.16
    ों
    1.15
    то
    1.14
     ifs
    1.13
    க
    1.13
     chacun
    1.12
    POSITIVE LOGITS
     گا۔
    1.24
    .}$
    1.16
    .。
    1.10
    ‌.
    1.09
    .~\
    1.08
     گی۔
    1.08
    ፨
    1.03
    infodisc
    1.02
    輳
    1.02
    oğlu
    1.02
    Act Density 0.004%

    No Known Activations