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

    Neuronpedia

    INDEX
    Explanations

    psychotic break, hallucinations, paranoia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UNNEEDED
    0.44
    sting
    0.44
    苦手
    0.39
    ˄
    0.39
     неравен
    0.39
    嚿
    0.39
    পুণ
    0.38
    잽
    0.38
     অসম
    0.38
     CLIENTI
    0.38
    POSITIVE LOGITS
     psychosis
    1.98
     psychotic
    1.87
     insanity
    1.72
     madness
    1.70
     hallucinations
    1.59
     sanity
    1.58
     delusional
    1.55
     halluc
    1.53
     delusions
    1.50
     schizophren
    1.48
    Act Density 0.092%

    No Known Activations