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

    Neuronpedia

    INDEX
    Explanations

    numerical constants

    np_max-act · gemini-2.0-flash

    The neuron never fires on any token—it’s essentially a dead (unused) detector.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uar
    -0.06
     NSK
    -0.06
     Standard
    -0.06
    .IsNullOr
    -0.06
     AFL
    -0.06
    .prot
    -0.06
    /**↵
    -0.06
     anguish
    -0.06
    corr
    -0.06
     hebben
    -0.06
    POSITIVE LOGITS
     Каз
    0.07
    щего
    0.06
    -Russian
    0.06
    qui
    0.06
     İt
    0.06
    TextEdit
    0.06
    voie
    0.06
     EDIT
    0.06
     vypad
    0.06
     succes
    0.06
    Act Density 0.009%

    No Known Activations