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

    Neuronpedia

    INDEX
    Explanations

    culture typograph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eine
    0.36
    bus
    0.35
    Unser
    0.34
    0.33
     kter
    0.33
    ה
    0.33
    !!.
    0.33
    ẹt
    0.33
    Loan
    0.32
    has
    0.31
    POSITIVE LOGITS
     biore
    0.35
     РАН
    0.32
     resources
    0.32
     regimes
    0.31
    資源
    0.30
     Cultures
    0.30
    創
    0.30
     anticip
    0.29
     cohesion
    0.29
    之一
    0.29
    Act Density 0.001%

    No Known Activations