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

    Neuronpedia

    INDEX
    Explanations

    properties and keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imd
    -0.07
     Circus
    -0.07
    interfaces
    -0.06
    Charset
    -0.06
     '^
    -0.06
     problème
    -0.06
     cucumber
    -0.06
     jste
    -0.06
     су
    -0.06
    كو
    -0.06
    POSITIVE LOGITS
    roleum
    0.07
    िकल
    0.06
    рип
    0.06
    charted
    0.06
    씀
    0.06
    ("""↵
    0.06
     назнач
    0.06
    >)↵
    0.06
    ožná
    0.06
    .setResult
    0.06
    Act Density 0.050%

    No Known Activations