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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the special “gpt_data” marker (and its surrounding underscores/quotes) that denote the required output string format.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Haut
    -0.07
     small
    -0.07
    mp
    -0.06
     perfect
    -0.06
    Suite
    -0.06
     skal
    -0.06
     Suite
    -0.06
    ите
    -0.06
     �
    -0.06
     realized
    -0.06
    POSITIVE LOGITS
     Çalış
    0.08
    OptionsMenu
    0.06
     schematic
    0.06
    _ing
    0.06
    .try
    0.06
    .Uri
    0.06
    avel
    0.06
    ']*
    0.06
     ********************************************************
    0.06
     dej
    0.06
    Act Density 0.307%

    No Known Activations