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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⿸
    0.39
    Foldout
    0.38
    旿
    0.38
    黑
    0.37
    nbsp
    0.36
    ँ
    0.36
    0.35
    ändige
    0.35
    柅
    0.35
    २
    0.34
    POSITIVE LOGITS
     pozor
    0.39
    .
    0.37
     up
    0.35
     magnesium
    0.34
     enk
    0.33
    .}$
    0.33
     pulverized
    0.33
     penge
    0.32
    ദ്
    0.32
     viktig
    0.32
    Act Density 0.000%

    No Known Activations