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

    Neuronpedia

    INDEX
    Explanations

    single digits

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric version‐number segments (decimal components) in package or dependency version strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    haft
    -0.07
    istem
    -0.07
    敷
    -0.06
    /desktop
    -0.06
    OCKET
    -0.06
    ısından
    -0.06
    market
    -0.06
    傳
    -0.06
    elder
    -0.06
    EM
    -0.05
    POSITIVE LOGITS
     Students
    0.08
    -popup
    0.07
     matching
    0.07
     pushing
    0.07
    Acceler
    0.07
     With
    0.07
     Assurance
    0.06
     bacheca
    0.06
    _DAC
    0.06
     making
    0.06
    Act Density 0.021%

    No Known Activations