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

    Neuronpedia

    INDEX
    Explanations

    logarithm and user profile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     None
    0.41
     Gru
    0.41
     none
    0.39
     suppression
    0.37
     suppressing
    0.36
    ts
    0.36
    hana
    0.35
     suppressed
    0.35
     infer
    0.35
    refresh
    0.35
    POSITIVE LOGITS
    assadors
    0.42
    ⓶
    0.42
     жүктөө
    0.39
     warl
    0.38
    েষে
    0.38
     TabLayout
    0.37
     المقسوم
    0.37
     матри
    0.37
     Fleurit
    0.37
     dirigeants
    0.36
    Act Density 0.000%

    No Known Activations