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

    Neuronpedia

    INDEX
    Explanations

    crown and crowned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.45
    ल
    1.32
     as
    1.30
    ف
    1.30
    ק
    1.24
    ;
    1.23
    ص
    1.23
    ل
    1.20
    ا
    1.18
    व
    1.18
    POSITIVE LOGITS
    ↵
    1.23
    4
    1.08
    atir
    1.03
    5
    1.02
    ۹
    1.02
    им
    1.02
    ukul
    0.96
    एस
    0.94
    ин
    0.93
    this
    0.93
    Act Density 0.011%

    No Known Activations