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

    Neuronpedia

    INDEX
    Explanations

    illegal and unethical activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     শব্দের
    0.33
     Notifications
    0.32
     hurtful
    0.32
     tolerant
    0.31
     Dialog
    0.31
     பயன்ப
    0.31
     Violence
    0.31
     köt
    0.31
     সহজেই
    0.31
     ਜਾਂ
    0.31
    POSITIVE LOGITS
     manufacture
    0.46
     tampering
    0.45
     soliciting
    0.43
     fals
    0.43
     downloading
    0.43
     divul
    0.43
     Attempt
    0.42
     knowingly
    0.42
     conspiring
    0.42
     attempted
    0.41
    Act Density 0.035%

    No Known Activations