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

    Neuronpedia

    INDEX
    Explanations

    pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ardından
    0.20
     unsupported
    0.20
    ającym
    0.19
    소를
    0.19
     perman
    0.19
     gouttes
    0.19
    ^*$
    0.19
     polytopes
    0.19
     dissol
    0.18
    bouncer
    0.18
    POSITIVE LOGITS
    :
    0.33
    ：
    0.32
    ៈ
    0.31
     Provides
    0.30
    。
    0.29
     Extremely
    0.28
     मानता
    0.27
    Allows
    0.27
    ։
    0.27
     :
    0.27
    Act Density 0.167%

    No Known Activations