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

    Neuronpedia

    INDEX
    Explanations

    what is essentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ipur
    0.84
    들을
    0.80
    launcher
    0.73
    들과
    0.73
     glued
    0.72
     पहलवान
    0.70
     학생들이
    0.70
     bunlar
    0.69
    他們
    0.69
     ඒවා
    0.68
    POSITIVE LOGITS
     defined
    1.22
    defined
    1.19
    Defined
    1.13
     Defined
    1.12
     definida
    1.12
     definido
    1.01
     définie
    1.00
     whereby
    1.00
     ситуации
    0.94
    Cuando
    0.93
    Act Density 0.330%

    No Known Activations