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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash

    The neuron flags subjective or evaluative language—words that express emotion, opinion, or judgment.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Profile
    -0.06
    आ
    -0.06
    erd
    -0.06
    enheim
    -0.06
    Vault
    -0.06
     oldValue
    -0.06
     workout
    -0.06
    Biz
    -0.06
    ISTORY
    -0.06
     Attend
    -0.06
    POSITIVE LOGITS
     Т
    0.07
     anal
    0.07
    CONT
    0.06
     перест
    0.06
    串
    0.06
     belang
    0.06
     hurting
    0.06
     currencies
    0.06
     piş
    0.06
     pron
    0.06
    Act Density 0.182%

    No Known Activations