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

    Neuronpedia

    INDEX
    Explanations

    latex commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vieve
    0.37
    oons
    0.35
    Speaking
    0.34
     เส
    0.34
    speaking
    0.33
     gums
    0.33
    bew
    0.32
    Salem
    0.32
    ூழ
    0.32
    ranged
    0.32
    POSITIVE LOGITS
    mathbf
    0.45
    textbf
    0.43
    textrm
    0.41
     today
    0.40
     bf
    0.40
    bf
    0.39
    rightarrow
    0.38
    textit
    0.36
     nostri
    0.36
    textup
    0.35
    Act Density 0.002%

    No Known Activations