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

    Neuronpedia

    INDEX
    Explanations

    criticism

    np_max-act · gemini-2.0-flash

    The neuron never fires—it does not detect any token or pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _compile
    -0.07
    _US
    -0.06
     STATIC
    -0.06
     sed
    -0.06
    806
    -0.06
     contraseña
    -0.05
    祥
    -0.05
    자
    -0.05
     Tanrı
    -0.05
    овано
    -0.05
    POSITIVE LOGITS
     dunk
    0.07
     Nashville
    0.07
     primitives
    0.07
    認
    0.07
    avez
    0.07
    _INET
    0.07
    认
    0.06
    �
    0.06
    �
    0.06
    Ant
    0.06
    Act Density 0.033%

    No Known Activations