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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    This neuron activates on the token “If,” effectively detecting conditional statements or clauses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    battery
    -0.07
    flake
    -0.06
    drink
    -0.06
    biology
    -0.06
    итель
    -0.06
    IENCE
    -0.06
    delimiter
    -0.06
    _pin
    -0.06
    люч
    -0.06
     diamonds
    -0.06
    POSITIVE LOGITS
     experimentation
    0.07
    فن
    0.06
     Пари
    0.06
    .";
    0.06
    !");
    0.06
    (dat
    0.06
    	UINT
    0.06
     ek
    0.06
     asn
    0.06
    ";}↵
    0.06
    Act Density 0.017%

    No Known Activations