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

    Neuronpedia

    INDEX
    Explanations

    being subjected to judgment or mistreatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encouraged
    0.46
     allowed
    0.45
    dn
    0.44
     granted
    0.44
     equipped
    0.41
     instilled
    0.41
     able
    0.41
     ausgestattet
    0.39
     unleashed
    0.39
     seeking
    0.39
    POSITIVE LOGITS
     manipulated
    0.57
     talked
    0.56
     photographed
    0.55
     chatted
    0.55
     dominated
    0.53
     sinned
    0.52
     disagreed
    0.52
    watched
    0.51
    dominated
    0.51
     watched
    0.50
    Act Density 0.016%

    No Known Activations