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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal points (i.e. floating‐point numbers, such as reporter citations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    duck
    -0.07
     unconscious
    -0.06
     REM
    -0.06
     эт
    -0.06
    □□
    -0.06
     leftovers
    -0.06
     врем
    -0.06
     організації
    -0.06
    拉
    -0.06
    WW
    -0.06
    POSITIVE LOGITS
    _fk
    0.07
    actal
    0.07
    equ
    0.07
     Quantum
    0.07
    -rad
    0.06
    ERSHEY
    0.06
     �
    0.06
     продуктов
    0.06
     perl
    0.06
    	btn
    0.06
    Act Density 0.002%

    No Known Activations