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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    failed
    -0.07
     HD
    -0.07
     αρι
    -0.07
     setHidden
    -0.07
     الأرض
    -0.07
    zzo
    -0.06
     PCs
    -0.06
     cyc
    -0.06
     shiny
    -0.06
    oundation
    -0.06
    POSITIVE LOGITS
    (hero
    0.06
     GetValue
    0.06
     Mei
    0.06
     Comment
    0.06
     marched
    0.06
     musí
    0.06
    ni
    0.06
     """↵↵
    0.06
     parl
    0.06
     Challenge
    0.06
    Act Density 0.033%

    No Known Activations