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

    Neuronpedia

    INDEX
    Explanations

    service reviews

    np_max-act · gemini-2.0-flash

    This neuron detects personal‐testimonial language, especially first‐person pronouns and experience‐reporting verbs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้น
    -0.06
     bran
    -0.06
    %%%%%%%%
    -0.06
    Integrated
    -0.06
    WO
    -0.06
    (metrics
    -0.06
    923
    -0.06
    ano
    -0.06
     erroneous
    -0.06
     Bran
    -0.06
    POSITIVE LOGITS
     LETTER
    0.07
     одні
    0.07
     friend
    0.06
     kostenlos
    0.06
    engage
    0.06
    \f
    0.06
     Huyện
    0.06
     앉
    0.06
    	extern
    0.06
    (withId
    0.06
    Act Density 0.028%

    No Known Activations