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

    Neuronpedia

    INDEX
    Explanations

    exploit, abuse, endanger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReferencePose
    0.45
    DeferredGroup
    0.42
     savages
    0.42
    只能
    0.42
     আলোচনার
    0.41
     ivvu
    0.41
     sociedade
    0.41
     artères
    0.41
     allerede
    0.40
     население
    0.39
    POSITIVE LOGITS
     exploits
    0.47
     exploit
    0.47
     explo
    0.46
     tempt
    0.44
     N
    0.43
     exploited
    0.43
     exploitation
    0.41
     Tempt
    0.41
    explo
    0.40
     entice
    0.40
    Act Density 0.005%

    No Known Activations