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

    Neuronpedia

    INDEX
    Explanations

    financial investments

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens (especially decimal‐formatted values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     çat
    -0.07
    ap
    -0.06
    іх
    -0.06
     Kürt
    -0.06
    έ
    -0.06
     goodness
    -0.06
     downhill
    -0.06
    .RUN
    -0.06
    eným
    -0.06
    ride
    -0.06
    POSITIVE LOGITS
    Multi
    0.07
     нов
    0.07
     traveller
    0.06
     Multi
    0.06
     carrots
    0.06
    ยม
    0.06
     період
    0.06
    cooked
    0.06
    أة
    0.06
     μεγ
    0.06
    Act Density 0.008%

    No Known Activations