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

    Neuronpedia

    INDEX
    Explanations

    hypothetical scenarios

    np_max-act · gemini-2.0-flash

    The neuron detects past‐conditional or counterfactual constructions (e.g. “would have,” “had been”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     نیست
    -0.06
    -cons
    -0.06
    诊
    -0.06
     uğ
    -0.06
     horrific
    -0.06
     rifle
    -0.06
    े↵
    -0.06
    .age
    -0.06
    entered
    -0.06
     momentos
    -0.06
    POSITIVE LOGITS
     DEF
    0.07
    zą
    0.07
    acute
    0.06
    อห
    0.06
    (ball
    0.06
    _ARROW
    0.06
    _PED
    0.06
     bridal
    0.06
     dereg
    0.06
    actice
    0.06
    Act Density 0.039%

    No Known Activations