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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Facial
    -0.06
    gnu
    -0.06
    ='./
    -0.06
     nostro
    -0.06
     dishonest
    -0.06
    (CG
    -0.06
    forget
    -0.06
     HE
    -0.06
     wards
    -0.06
    ORIES
    -0.06
    POSITIVE LOGITS
     reporter
    0.07
    .invokeLater
    0.06
    .isHidden
    0.06
    Composer
    0.06
    (Un
    0.06
     nové
    0.06
    عية
    0.06
     illustrate
    0.06
    ，每
    0.06
    jon
    0.06
    Act Density 0.023%

    No Known Activations