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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the shell “source” (dot) commands (i.e. lines beginning with “.” to include another script).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bdd
    -0.07
    "If
    -0.06
     truthful
    -0.06
     Kaz
    -0.06
    Operator
    -0.06
     SCP
    -0.06
    Age
    -0.06
     courseId
    -0.06
    repeat
    -0.06
     ملی
    -0.06
    POSITIVE LOGITS
    失
    0.07
     Ens
    0.07
    _ARB
    0.07
     cunt
    0.06
     hindsight
    0.06
    acobian
    0.06
    ąd
    0.06
     discovery
    0.06
     -*-↵↵
    0.06
     ürünleri
    0.06
    Act Density 0.002%

    No Known Activations