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

    Neuronpedia

    INDEX
    Explanations

    Contrasting two things

    np_max-act · gemini-2.0-flash

    The neuron responds to words signaling contrast or comparison (e.g. “contrast,” “NOT”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Plato
    -0.07
     dealloc
    -0.07
     jdbc
    -0.06
     *_
    -0.06
    ่อไป
    -0.06
    _TypeInfo
    -0.06
     cria
    -0.06
    rades
    -0.06
    (heap
    -0.06
     Histogram
    -0.06
    POSITIVE LOGITS
    _CHAN
    0.06
    receive
    0.06
     �
    0.06
     dazu
    0.06
    _UPDATE
    0.06
     UNIX
    0.06
     biết
    0.06
    лин
    0.06
    _router
    0.06
    _HERE
    0.06
    Act Density 0.045%

    No Known Activations