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

    Neuronpedia

    INDEX
    Explanations

    square root checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lou
    0.39
     দর্শক
    0.38
     lateral
    0.38
     подпис
    0.37
     pal
    0.36
     proguardFiles
    0.36
    bracketing
    0.35
    SOLUTION
    0.35
     unsol
    0.35
    رمز
    0.34
    POSITIVE LOGITS
    ceil
    0.51
     Ceiling
    0.45
     ceiling
    0.44
    plaf
    0.42
     ceilings
    0.40
     অঞ্চ
    0.39
     ceil
    0.38
    possibly
    0.38
     необходимость
    0.38
     प्रीत
    0.38
    Act Density 0.010%

    No Known Activations