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

    Neuronpedia

    INDEX
    Explanations

    cocktail

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Şimdi
    -0.07
     Airport
    -0.07
     land
    -0.07
     temperatures
    -0.07
    将军
    -0.07
     escaping
    -0.06
     Building
    -0.06
    vector
    -0.06
     units
    -0.06
    (k
    -0.06
    POSITIVE LOGITS
    卺
    0.08
    トー
    0.07
    くなり
    0.07
    Ⓔ
    0.07
     recreate
    0.07
     Brighton
    0.07
    �
    0.07
    .Strict
    0.07
    埏
    0.06
    QC
    0.06
    Act Density 0.007%

    No Known Activations