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

    Neuronpedia

    INDEX
    Explanations

    unethical or illegal actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zowel
    0.29
    शरी
    0.28
     apartamento
    0.27
    嵓
    0.27
     சுதந்திர
    0.27
     cytosol
    0.27
     கடல்
    0.27
     இங்கு
    0.26
     तैयारी
    0.26
    選び
    0.26
    POSITIVE LOGITS
     penalties
    0.34
     detractors
    0.33
     egregious
    0.32
     rebut
    0.32
     obfusc
    0.31
     indict
    0.31
     condemn
    0.30
     disruptions
    0.30
     fraud
    0.29
     nuis
    0.29
    Act Density 0.000%

    No Known Activations