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

    Neuronpedia

    INDEX
    Explanations

    1-800 numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⴱ
    0.37
    ༠
    0.37
     jasno
    0.35
     বরং
    0.35
    ikor
    0.35
     ближе
    0.34
    Ϊ
    0.34
    reira
    0.34
    ylabel
    0.33
    ylinder
    0.33
    POSITIVE LOGITS
     احتم
    0.36
     Americans
    0.35
    Americans
    0.35
    Ა
    0.34
     gesam
    0.34
    ու
    0.34
     sixteen
    0.34
     probable
    0.33
     Prob
    0.33
    ６
    0.33
    Act Density 0.058%

    No Known Activations