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

    Neuronpedia

    INDEX
    Explanations

    command execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ण्ट
    0.50
    NeedConnect
    0.48
     protección
    0.48
    !',
    0.47
     mailed
    0.47
     guarded
    0.46
     nuov
    0.46
     Germanic
    0.46
    ভক্ত
    0.46
     subd
    0.45
    POSITIVE LOGITS
     this
    0.50
    Ps
    0.46
     Dylan
    0.45
     Rect
    0.45
      
    0.43
     it
    0.42
     Oliver
    0.41
     heave
    0.41
    দেশ
    0.40
     Eps
    0.40
    Act Density 0.002%

    No Known Activations