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

    Neuronpedia

    INDEX
    Explanations

    normal

    np_max-act · gemini-2.0-flash

    This neuron detects reassurance language indicating that something is normal or common (e.g., words like “normal,” “common,” and similar).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .navigate
    -0.07
    callback
    -0.06
     Арх
    -0.06
     분야
    -0.06
    .loading
    -0.06
     injustice
    -0.06
     Masters
    -0.06
    слов
    -0.06
     кого
    -0.06
     Basically
    -0.06
    POSITIVE LOGITS
    ¿
    0.08
    itized
    0.07
    /L
    0.07
    /R
    0.06
    인지
    0.06
     settling
    0.06
    jezd
    0.06
     theoretical
    0.06
     Arist
    0.06
     fd
    0.06
    Act Density 0.010%

    No Known Activations