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

    Neuronpedia

    INDEX
    Explanations

    practice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ultr
    -0.27
    ucas
    -0.26
    idas
    -0.25
    space
    -0.25
    æ·ĭ
    -0.24
    sc
    -0.24
    åĩºçĶŁ
    -0.24
    ulis
    -0.24
     whistle
    -0.24
    Unexpected
    -0.24
    POSITIVE LOGITS
    theless
    0.29
     guarding
    0.26
     predecessor
    0.25
    ÃĸZ
    0.24
    ROUGH
    0.24
    æįĨç»ij
    0.24
    åľ¨ä¸Ĭæµ·
    0.23
    RESSED
    0.23
    OldData
    0.23
    Hosting
    0.23
    Act Density 0.045%

    No Known Activations