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

    Neuronpedia

    INDEX
    Explanations

    yll

    np_max-act · gemini-2.0-flash

    The neuron remains inactive across all input tokens and thus does not detect any particular text pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .annotation
    -0.07
     getUsername
    -0.07
     너무
    -0.07
    _io
    -0.06
     venir
    -0.06
     Terminator
    -0.06
    ака
    -0.06
     pocket
    -0.06
    ilater
    -0.06
    .mob
    -0.06
    POSITIVE LOGITS
    ião
    0.07
     teaching
    0.06
    Cream
    0.06
    ılığ
    0.06
    yll
    0.06
     millones
    0.06
    睡
    0.06
    ],
    0.06
    rophy
    0.06
    .child
    0.06
    Act Density 0.002%

    No Known Activations