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

    Neuronpedia

    INDEX
    Explanations

    Code/website errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >k
    -0.07
     FLAG
    -0.06
     freezer
    -0.06
     carrots
    -0.06
    ekt
    -0.06
     mie
    -0.06
     UPS
    -0.06
    _tokens
    -0.06
    ičky
    -0.06
     flop
    -0.06
    POSITIVE LOGITS
    .Dense
    0.07
     Animated
    0.07
     isnt
    0.07
     있어서
    0.06
    ались
    0.06
    協
    0.06
     […]...↵
    0.06
    .Matrix
    0.06
     المهنة
    0.06
    NTSTATUS
    0.06
    Act Density 0.004%

    No Known Activations