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

    Neuronpedia

    INDEX
    Explanations

    because

    np_max-act · gemini-2.0-flash

    This neuron detects the causal conjunction “because.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <n
    -0.07
    _pts
    -0.07
    11
    -0.07
    Split
    -0.07
     span
    -0.07
    ANTLR
    -0.07
    54
    -0.07
     std
    -0.07
    (tol
    -0.07
     ladder
    -0.07
    POSITIVE LOGITS
     because
    0.22
    because
    0.20
     Because
    0.18
    Because
    0.16
    ecause
    0.11
     cuz
    0.10
     porque
    0.10
    cause
    0.09
     لأن
    0.09
    Although
    0.08
    Act Density 0.045%

    No Known Activations