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

    Neuronpedia

    INDEX
    Explanations

    predicted/expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sz
    -0.07
    สก
    -0.06
    //------------------------------------------------------------------------------------------------
    -0.06
     ski
    -0.06
    .story
    -0.06
     قرار
    -0.06
    ","",
    -0.06
    stdafx
    -0.06
    <boolean
    -0.06
    (sz
    -0.06
    POSITIVE LOGITS
     pensar
    0.07
     LX
    0.07
    )}↵↵
    0.07
    ена
    0.07
    rition
    0.07
    inář
    0.07
     완
    0.06
    eral
    0.06
    .Reg
    0.06
    .fromRGBO
    0.06
    Act Density 0.021%

    No Known Activations