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

    Neuronpedia

    INDEX
    Explanations

    facebook marketplace links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एक्चु
    0.41
    掻
    0.39
    觫
    0.38
    ensureEqual
    0.37
    ಹೆ
    0.36
    buildSpec
    0.36
     maksimum
    0.36
    ⵚ
    0.36
     ऑग
    0.36
     लेट्स
    0.35
    POSITIVE LOGITS
    0.45
      
    0.37
     @
    0.36
     form
    0.35
     feuilles
    0.35
    )
    0.35
     r
    0.34
    and
    0.34
     email
    0.33
    r
    0.33
    Act Density 0.001%

    No Known Activations