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

    Neuronpedia

    INDEX
    Explanations

    code or versions

    np_max-act · gemini-2.0-flash

    This neuron detects software version strings composed of digits and dots.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     approach
    -0.07
     Mountains
    -0.07
     Approach
    -0.06
    analy
    -0.06
     accreditation
    -0.06
    ではなく
    -0.06
    튼
    -0.06
     Aust
    -0.06
    ¨ط
    -0.06
     明
    -0.06
    POSITIVE LOGITS
    .gr
    0.07
     صن
    0.06
    续
    0.06
    Printer
    0.06
    装
    0.06
     adec
    0.06
    855
    0.06
     يت
    0.06
    _dates
    0.06
    pons
    0.06
    Act Density 0.018%

    No Known Activations