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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect the licensing boilerplate phrase “under the terms of the.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (klass
    -0.07
    찰
    -0.07
    「あ
    -0.07
    농
    -0.06
     так
    -0.06
    иш
    -0.06
     род
    -0.06
    (JNIEnv
    -0.06
    想要
    -0.06
    semb
    -0.06
    POSITIVE LOGITS
    "".
    0.07
     frec
    0.07
    (length
    0.06
    Guess
    0.06
     (↵↵
    0.06
     Mouth
    0.06
    upe
    0.06
     roce
    0.06
    _claim
    0.06
     اگر
    0.06
    Act Density 0.000%

    No Known Activations