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

    Neuronpedia

    INDEX
    Explanations

    actual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Column
    -0.07
    )})↵
    -0.07
    ?↵↵
    -0.07
    (".");↵
    -0.06
    ">';↵
    -0.06
    }';↵
    -0.06
    (TimeSpan
    -0.06
    :");↵↵
    -0.06
    pegawai
    -0.06
    (Some
    -0.06
    POSITIVE LOGITS
     checkout
    0.07
     Kahn
    0.07
    utch
    0.07
     showcasing
    0.06
     registered
    0.06
     Window
    0.06
     predict
    0.06
    ortex
    0.06
     puerto
    0.06
    eb
    0.06
    Act Density 0.001%

    No Known Activations