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

    Neuronpedia

    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash

    The neuron activates on the "'th" suffix in ordinal expressions (e.g. “nth term”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	temp
    -0.08
     Offensive
    -0.07
     cards
    -0.07
    .Change
    -0.06
     protests
    -0.06
    	range
    -0.06
     sayesinde
    -0.06
    Interrupt
    -0.06
     commune
    -0.06
     bureau
    -0.06
    POSITIVE LOGITS
    .xmlbeans
    0.07
    lassen
    0.07
     плав
    0.06
    iblings
    0.06
    �
    0.06
    .ColumnName
    0.06
     재
    0.06
    uthor
    0.06
    еди
    0.06
    %',↵
    0.06
    Act Density 0.001%

    No Known Activations