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

    Neuronpedia

    INDEX
    Explanations

    LaTeX packages and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Phase
    0.80
     Appliance
    0.80
     Labs
    0.72
     Hormone
    0.72
     AIDS
    0.71
     values
    0.71
     phage
    0.69
     EXE
    0.68
     phase
    0.68
     Creations
    0.68
    POSITIVE LOGITS
    Confirmation
    0.67
    Blind
    0.66
    graphicx
    0.65
    tik
    0.64
    nikom
    0.63
    ruciating
    0.63
     پیشن
    0.63
     алгорит
    0.62
    algorithm
    0.62
    TikTok
    0.62
    Act Density 0.004%

    No Known Activations