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

    Neuronpedia

    INDEX
    Explanations

    if i recall correctly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ти
    2.33
    ми
    1.90
    تان
    1.80
    Fullscreen
    1.77
    که
    1.75
    Cob
    1.71
    {
    1.69
    equ
    1.68
    al
    1.68
    kia
    1.67
    POSITIVE LOGITS
    чество
    1.85
    ባድ
    1.74
    чков
    1.73
    vendors
    1.70
     regiments
    1.70
     semisimple
    1.70
    irittura
    1.69
    犇
    1.66
     pertinentes
    1.65
     Kroger
    1.64
    Act Density 0.000%

    No Known Activations