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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    This neuron detects HTML `<i>` elements (and similar tags) used for icon fonts (e.g. those with classes like `icon-…`, `fa …`, `glyphicon …`, or `ion-…`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /+
    -0.06
     hạ
    -0.06
    eer
    -0.06
     तब
    -0.06
    Bot
    -0.06
    erif
    -0.06
    -parent
    -0.06
    Powered
    -0.05
    xAE
    -0.05
    .Access
    -0.05
    POSITIVE LOGITS
    right
    0.07
    )","
    0.07
     Emotional
    0.06
     EINA
    0.06
    prompt
    0.06
     eliminar
    0.06
    ]=='
    0.06
    -hard
    0.06
     entidad
    0.06
     každý
    0.06
    Act Density 0.001%

    No Known Activations