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

    Neuronpedia

    INDEX
    Explanations

    rink

    np_max-act · gemini-2.0-flash

    The neuron responds to fragments of personal names (particularly surnames) regardless of context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -Line
    -0.07
    	col
    -0.07
    /tutorial
    -0.07
     sons
    -0.06
     вк
    -0.06
    dq
    -0.06
    _DD
    -0.06
     Knight
    -0.06
     Format
    -0.06
    iddleware
    -0.06
    POSITIVE LOGITS
     DropIndex
    0.06
     куст
    0.06
     अख
    0.06
    
    0.06
    _ALIGN
    0.06
    .keySet
    0.06
    ritz
    0.06
     JFactory
    0.06
     มหาว
    0.06
     Česká
    0.06
    Act Density 0.140%

    No Known Activations