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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertIsNot
    -0.07
    Jam
    -0.07
     hay
    -0.07
    אלוהים
    -0.07
     native
    -0.06
     ли
    -0.06
    redni
    -0.06
    หย
    -0.06
     cac
    -0.06
    뜯
    -0.06
    POSITIVE LOGITS
    纺织
    0.07
    .')↵↵
    0.06
    -string
    0.06
     disag
    0.06
     uncertainties
    0.06
    Ana
    0.06
    utive
    0.06
    processor
    0.06
    >";↵↵
    0.06
    .*;
↵
↵
    0.06
    Act Density 0.078%

    No Known Activations