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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash

    The neuron detects segments of user‐interface text that announce supported browsers (e.g. “We support the following browsers: …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    gettext
    -0.06
    Lv
    -0.06
    .metamodel
    -0.06
    Rather
    -0.06
     loro
    -0.06
    Fail
    -0.06
    .notifications
    -0.06
    хів
    -0.06
     必
    -0.06
    ustum
    -0.06
    POSITIVE LOGITS
    omp
    0.06
    osci
    0.06
     Apart
    0.06
    .Claims
    0.06
    primary
    0.06
     Expert
    0.06
    route
    0.06
     second
    0.06
    урс
    0.06
    _full
    0.06
    Act Density 0.001%

    No Known Activations