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

    Neuronpedia

    INDEX
    Explanations

    Code/metadata

    np_max-act · gemini-2.0-flash

    The neuron primarily detects the special end‐of‐text marker token (“<|eot_id|>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     setStatus
    -0.07
    (icon
    -0.07
    dělen
    -0.07
     yaz
    -0.06
    igth
    -0.06
     bal
    -0.06
     آز
    -0.06
     yang
    -0.06
    brightness
    -0.06
    (bin
    -0.06
    POSITIVE LOGITS
    κε
    0.07
     believes
    0.07
     epis
    0.07
     farther
    0.07
    /mysql
    0.06
    inea
    0.06
    subscribe
    0.06
    ِب
    0.06
    .au
    0.06
     believe
    0.06
    Act Density 0.051%

    No Known Activations