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

    Neuronpedia

    INDEX
    Explanations

    O

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    关心
    -0.08
     Chicken
    -0.07
    attention
    -0.07
    )))↵↵↵
    -0.07
     Settings
    -0.07
    entialAction
    -0.07
    extra
    -0.06
     StreamLazy
    -0.06
     Mapping
    -0.06
     Đông
    -0.06
    POSITIVE LOGITS
     unlocks
    0.08
    玞
    0.07
     مما
    0.07
    asury
    0.07
    .gsub
    0.07
    不得已
    0.06
     уникальн
    0.06
    美的
    0.06
    天然
    0.06
    ----------</
    0.06
    Act Density 0.000%

    No Known Activations