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

    Neuronpedia

    INDEX
    Explanations

    acknowledging feelings and offering support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Psik
    0.44
     psicologia
    0.43
     amused
    0.42
     Caution
    0.40
    楽しみ
    0.40
     mischiev
    0.40
     geworden
    0.39
    变为
    0.39
    Caution
    0.38
     Psychological
    0.38
    POSITIVE LOGITS
     feelings
    0.62
    Whatever
    0.60
     whatever
    0.57
     bottling
    0.56
     Whatever
    0.54
     acknowledging
    0.54
     remember
    0.53
    whatever
    0.52
    acknowledge
    0.52
     Feelings
    0.52
    Act Density 0.089%

    No Known Activations