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

    Neuronpedia

    INDEX
    Explanations

    . May ultimately empower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cosmos
    0.40
     zodiac
    0.39
     etiology
    0.38
     gadgets
    0.37
    CTS
    0.37
     étude
    0.35
    िवर्स
    0.34
     shoe
    0.34
    പ്പ്
    0.34
     året
    0.34
    POSITIVE LOGITS
    return
    0.37
    ++
    0.33
    tkWidget
    0.33
    aneamente
    0.32
    responsive
    0.32
    hese
    0.32
    akkhati
    0.31
    ceased
    0.30
    ged
    0.30
    paused
    0.30
    Act Density 0.019%

    No Known Activations