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

    Neuronpedia

    INDEX
    Explanations

    /*

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any tokens—it remains inactive (a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    atisch
    -0.07
     ********************************************************
    -0.06
     contraseña
    -0.06
    #from
    -0.06
    icao
    -0.06
    üml
    -0.06
     Er
    -0.06
    -enter
    -0.06
     bombers
    -0.06
     aber
    -0.06
    POSITIVE LOGITS
     Hàng
    0.06
    _drag
    0.06
     ""
    0.06
    _imgs
    0.06
    .type
    0.06
     ره
    0.05
    ovable
    0.05
    >";
    0.05
    ultiply
    0.05
    	uint
    0.05
    Act Density 0.005%

    No Known Activations