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

    Neuronpedia

    INDEX
    Explanations

    Dutch and Florida

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ступ
    0.82
    何も
    0.79
    同じ
    0.78
     कोई
    0.78
    όν
    0.77
     more
    0.74
     Goku
    0.74
    ెక్
    0.73
     बोतल
    0.72
    tu
    0.72
    POSITIVE LOGITS
    ische
    1.08
    isch
    1.08
    rainian
    1.08
     polity
    1.07
    centric
    1.03
    ischen
    1.02
    어로
    1.00
     bureaucracy
    0.99
    దేశ
    0.98
    orsz
    0.97
    Act Density 1.520%

    No Known Activations