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

    Neuronpedia

    INDEX
    Explanations

    challenging negative thoughts with evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pkg
    0.44
     ssh
    0.42
     consciousness
    0.40
     incarn
    0.40
     شوق
    0.40
    ssh
    0.39
     aspirants
    0.39
     amni
    0.39
     sublicense
    0.38
     simulates
    0.38
    POSITIVE LOGITS
     Realistic
    0.66
     realistic
    0.59
     pessimistic
    0.59
     exaggerated
    0.56
     exager
    0.56
     exaggerate
    0.56
    Realistic
    0.55
     catast
    0.54
     Evidence
    0.53
    Evidence
    0.53
    Act Density 0.014%

    No Known Activations