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

    Neuronpedia

    INDEX
    Explanations

    Ann Arbor/Michigan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .omg
    -0.31
    èħĬ
    -0.28
    uga
    -0.27
     season
    -0.25
    O
    -0.25
    flare
    -0.25
    "
    -0.25
     karma
    -0.25
     arbitrarily
    -0.24
    ymbols
    -0.24
    POSITIVE LOGITS
    ioxide
    0.28
    igham
    0.28
    åIJĥ
    0.27
    æĥ³ä¸įåĪ°
    0.26
    ToF
    0.25
    ERR
    0.25
    æѦè£ħ
    0.24
    ãĥĮ
    0.23
    çı°
    0.23
    缴æİ¥
    0.23
    Act Density 0.436%

    No Known Activations