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

    Neuronpedia

    INDEX
    Explanations

    hypnosis

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens related to hypnosis—especially the “hypn-” root (e.g. hypnot, hypnosis, hypnotic) used in induction scripts and commands.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    تى
    -0.06
    иты
    -0.06
    できない
    -0.06
    gunta
    -0.06
    meli
    -0.06
    zzo
    -0.06
    tte
    -0.06
    pest
    -0.06
     دوره
    -0.06
     roli
    -0.06
    POSITIVE LOGITS
     quoi
    0.06
    ucer
    0.06
    urent
    0.06
     Ellie
    0.06
    叔
    0.06
    ователь
    0.06
    IconButton
    0.06
    _FILENO
    0.06
     backlog
    0.06
     Chanel
    0.06
    Act Density 0.013%

    No Known Activations