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

    Neuronpedia

    INDEX
    Explanations

    countries and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    寯
    0.34
    ripciones
    0.34
    ⼦
    0.33
     Everything
    0.33
    贞
    0.33
    俶
    0.33
     Animals
    0.33
    umptions
    0.33
    rizione
    0.32
     Beautiful
    0.32
    POSITIVE LOGITS
    等地
    0.33
     diante
    0.32
    most
    0.32
     notably
    0.32
     başta
    0.31
    kan
    0.31
    Greece
    0.30
    ಸ್ತು
    0.30
    Kan
    0.30
    particularly
    0.30
    Act Density 0.143%

    No Known Activations