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

    Neuronpedia

    INDEX
    Explanations

    Positive adjectives

    np_max-act · gemini-2.0-flash

    The neuron fires on subjective evaluative adjectives expressing positive judgment or praise (e.g., “cute,” “beautiful,” “adorable”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    记录
    -0.06
    .setFont
    -0.06
     shredded
    -0.06
    _THEME
    -0.06
     необхід
    -0.06
     десят
    -0.06
    redirectTo
    -0.06
     Lilly
    -0.06
     الانت
    -0.05
     레
    -0.05
    POSITIVE LOGITS
     cà
    0.08
     deser
    0.07
    ��
    0.07
     earm
    0.07
     Pek
    0.06
    017
    0.06
     Kah
    0.06
     había
    0.06
     aún
    0.06
     ninety
    0.06
    Act Density 0.038%

    No Known Activations