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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইনডাকশন
    0.38
     shove
    0.38
     значит
    0.37
    ется
    0.37
     ইনডাক
    0.37
     ventajas
    0.36
    జేపీ
    0.36
    etrot
    0.36
     корни
    0.36
     элект
    0.36
    POSITIVE LOGITS
     July
    0.47
     September
    0.47
    0.47
    عين
    0.47
    。
    0.45
    B
    0.44
    1
    0.43
    P
    0.43
     November
    0.43
     Additionally
    0.43
    Act Density 0.003%

    No Known Activations