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

    Neuronpedia

    INDEX
    Explanations

    anatomy and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.62
    ↵
    0.60
    ()
    0.49
    UC
    0.47
    1
    0.47
     .
    0.46
    ；
    0.46
    q
    0.45
    vm
    0.44
     Ма
    0.44
    POSITIVE LOGITS
     boobs
    0.46
     gyne
    0.46
     کافی
    0.45
     castration
    0.44
     laryng
    0.44
    蓍
    0.44
     washout
    0.44
    estä
    0.44
     booth
    0.43
    äus
    0.43
    Act Density 0.001%

    No Known Activations