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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the state or government (e.g., words like “state,” “government,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Riy
    -0.07
    遍
    -0.06
     навер
    -0.06
    尖
    -0.06
    _my
    -0.06
     cavern
    -0.06
    โต
    -0.06
     المع
    -0.06
    ungeon
    -0.06
    _OPTS
    -0.05
    POSITIVE LOGITS
    Slim
    0.07
    (Date
    0.07
     State
    0.07
    .platform
    0.07
     Estado
    0.07
     Shall
    0.06
    ?>:</
    0.06
    σκ
    0.06
     webcam
    0.06
     государ
    0.06
    Act Density 0.009%

    No Known Activations