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

    Neuronpedia

    INDEX
    Explanations

    (s

    np_max-act · gemini-2.0-flash

    This neuron never activates on any content—it appears to be effectively “dead” and does not detect any feature.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -hit
    -0.06
    amus
    -0.06
    佐
    -0.06
     wk
    -0.06
     харч
    -0.06
    貨
    -0.06
    엔
    -0.06
     SUV
    -0.06
    モン
    -0.06
     célib
    -0.06
    POSITIVE LOGITS
    ppv
    0.07
     composite
    0.07
     creatures
    0.07
    ="#"
    0.07
    들의
    0.06
     refs
    0.06
    getClient
    0.06
     shelters
    0.06
    Specifier
    0.06
    _failure
    0.06
    Act Density 0.008%

    No Known Activations