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

    Neuronpedia

    INDEX
    Explanations

    code/data with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achie
    -0.07
     ovarian
    -0.07
     kino
    -0.06
    シェ
    -0.06
     Laurie
    -0.06
    Spoiler
    -0.06
     Oculus
    -0.06
     telefone
    -0.06
     밀
    -0.06
    KeyType
    -0.06
    POSITIVE LOGITS
    .',
    0.07
    cl
    0.07
     advertise
    0.07
    νονται
    0.07
    layan
    0.06
    인데
    0.06
    Left
    0.06
    --↵
    0.06
     capacities
    0.06
     normally
    0.06
    Act Density 0.052%

    No Known Activations