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

    Neuronpedia

    INDEX
    Explanations

    Inability, impossibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fashionable
    -0.07
    Malloc
    -0.06
     cheap
    -0.06
     &,
    -0.06
     accepts
    -0.06
    [row
    -0.06
     modest
    -0.06
     đồng
    -0.06
     CONTRIBUT
    -0.06
    UBL
    -0.06
    POSITIVE LOGITS
     Stard
    0.07
    787
    0.07
    imiters
    0.07
     scrolls
    0.07
     هواپیم
    0.06
     Lauren
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ंस
    0.06
    ConnectionFactory
    0.06
    кой
    0.06
    Act Density 0.002%

    No Known Activations