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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron is detecting occurrences of the “if” keyword (i.e. conditional statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    うち
    -0.08
    nět
    -0.07
    EntryPoint
    -0.07
     kullanarak
    -0.07
     besteht
    -0.06
    lanma
    -0.06
     verir
    -0.06
    .Tele
    -0.06
    ниці
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     HUGE
    0.07
    ublished
    0.07
     AVAILABLE
    0.07
    Ui
    0.06
     TOM
    0.06
    _SIDE
    0.06
     prosecution
    0.06
     announcement
    0.06
     IF
    0.06
     Saw
    0.06
    Act Density 0.020%

    No Known Activations