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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rivers
    -0.08
    urga
    -0.07
     resultant
    -0.07
     staying
    -0.07
    ymm
    -0.06
    された
    -0.06
    ικών
    -0.06
    특별
    -0.06
    야
    -0.06
    rup
    -0.06
    POSITIVE LOGITS
     ре
    0.07
    „J
    0.07
    ？↵
    0.07
    ={()
    0.06
     ominous
    0.06
    >j
    0.06
    sy
    0.06
    .wr
    0.06
    Gi
    0.06
     klein
    0.06
    Act Density 0.065%

    No Known Activations