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

    Neuronpedia

    INDEX
    Explanations

    previous

    np_max-act · gemini-2.0-flash

    This neuron never activates (all recorded activations are zero), so it isn’t detecting any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ef
    -0.06
     gelen
    -0.06
     Shr
    -0.06
     Letter
    -0.06
    Draw
    -0.06
    ised
    -0.06
    人民
    -0.06
    ğiniz
    -0.06
    Sys
    -0.06
     Hay
    -0.06
    POSITIVE LOGITS
     dní
    0.07
     euros
    0.07
    .setDate
    0.07
    (score
    0.07
     ==(
    0.07
    ?,?,
    0.06
    <↵
    0.06
     heals
    0.06
     كم
    0.06
     lashes
    0.06
    Act Density 0.021%

    No Known Activations