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

    Neuronpedia

    INDEX
    Explanations

    By

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surla
    -0.59
    spania
    -0.50
    jednoc
    -0.49
    libatkan
    -0.47
    Біографія
    -0.47
    rairie
    -0.47
     nakalista
    -0.46
    gantian
    -0.46
     toepassing
    -0.46
    Lieferumfang
    -0.46
    POSITIVE LOGITS
     kaarangay
    0.62
     its
    0.57
     them
    0.57
    AnchorStyles
    0.56
     their
    0.53
    <bos>
    0.52
     another
    0.52
    الإنجليزية
    0.52
     an
    0.51
    Tug
    0.51
    Act Density 0.007%

    No Known Activations