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

    Neuronpedia

    INDEX
    Explanations

    remove

    np_max-act · gemini-2.0-flash

    This neuron activates on the keyword or identifier “delete” (e.g. flag names or parameters controlling deletion) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Permission
    -0.07
    říz
    -0.07
     Кар
    -0.06
     ecstasy
    -0.06
     kuk
    -0.06
    manual
    -0.06
     counted
    -0.06
     कल
    -0.06
    akk
    -0.06
     уник
    -0.06
    POSITIVE LOGITS
     Wet
    0.06
    *↵
    0.06
     Elev
    0.06
    .npy
    0.06
    ResponseStatus
    0.06
    ्वच
    0.06
     законом
    0.06
     专
    0.06
    advisor
    0.06
     Snow
    0.06
    Act Density 0.017%

    No Known Activations