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

    Neuronpedia

    INDEX
    Explanations

    come visit or by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seeking
    0.68
     requesting
    0.66
     asking
    0.61
     Seeking
    0.54
     talking
    0.53
    seeking
    0.53
     confrontation
    0.52
     meminta
    0.52
     proposing
    0.52
     contacting
    0.52
    POSITIVE LOGITS
     by
    0.45
    oleh
    0.42
    鲈
    0.42
     توسط
    0.40
    减
    0.40
     đấy
    0.40
    ことで
    0.39
    ensión
    0.39
    生存
    0.39
     દ્વારા
    0.39
    Act Density 0.002%

    No Known Activations