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

    Neuronpedia

    INDEX
    Explanations

    Positive sentiment

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on subjective first-person comments and personal reactions—i.e. “I” statements and evaluative/adjectival language expressing opinions or feelings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    包括
    -0.07
    Birth
    -0.07
     напис
    -0.06
    mh
    -0.06
    atas
    -0.06
     애
    -0.06
    籍
    -0.06
     looming
    -0.06
     могли
    -0.06
    ğit
    -0.06
    POSITIVE LOGITS
    _origin
    0.07
    .↵↵↵↵
    0.07
    	point
    0.07
    +B
    0.07
    _Version
    0.07
    Indiana
    0.07
    	account
    0.07
    	conf
    0.06
    %).↵↵
    0.06
    auté
    0.06
    Act Density 0.067%

    No Known Activations