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

    Neuronpedia

    INDEX
    Explanations

    disordered, newer, falling short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SOCK
    0.40
    сах
    0.39
     hí
    0.37
     "','"
    0.37
     стек
    0.37
    𝗵
    0.37
    笹
    0.37
    の名前
    0.37
     шей
    0.36
    átiles
    0.36
    POSITIVE LOGITS
     disposed
    0.53
     Disposition
    0.50
     disposition
    0.50
     dispositions
    0.48
     absurd
    0.46
     Disposal
    0.43
     dispos
    0.43
     disposal
    0.43
     tele
    0.42
     disposizione
    0.42
    Act Density 0.000%

    No Known Activations