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

    Neuronpedia

    INDEX
    Explanations

    hold

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “hold” (especially in “Hold’em”)—i.e. references to the poker variant Texas Hold’em.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    
    -0.06
     ब
    -0.06
    -Saharan
    -0.06
    756
    -0.06
     nửa
    -0.06
     BITS
    -0.06
     från
    -0.06
    .describe
    -0.06
     ihnen
    -0.06
    	grid
    -0.06
    POSITIVE LOGITS
    (call
    0.07
    .Companion
    0.07
     consistent
    0.06
    reg
    0.06
     regarding
    0.06
    venience
    0.06
    elle
    0.06
    �
    0.06
    uggestion
    0.06
     reckon
    0.06
    Act Density 0.003%

    No Known Activations