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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron responds to the phrase “series of.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ont
    -0.07
    bett
    -0.07
     indicator
    -0.07
     території
    -0.06
     ADHD
    -0.06
    elems
    -0.06
     allocation
    -0.06
     not
    -0.06
    (prediction
    -0.06
    ’ve
    -0.06
    POSITIVE LOGITS
     органів
    0.07
    .getRow
    0.07
    Forms
    0.07
     الناس
    0.07
    ousand
    0.07
     servo
    0.07
     خط
    0.06
     through
    0.06
    .Sys
    0.06
    _unref
    0.06
    Act Density 0.008%

    No Known Activations