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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron remains inactive and does not detect any particular tokens or patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     by
    -0.07
     этого
    -0.07
    成了
    -0.06
    _week
    -0.06
    bots
    -0.06
    一度
    -0.06
     рус
    -0.06
     примерно
    -0.06
     गए
    -0.06
     Raf
    -0.06
    POSITIVE LOGITS
     meilleure
    0.07
     deficient
    0.07
    -‐
    0.07
    (dynamic
    0.07
     servants
    0.06
    ---
↵
    0.06
     compete
    0.06
    xCC
    0.06
    endencies
    0.06
    VMLINUX
    0.06
    Act Density 0.053%

    No Known Activations