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

    Neuronpedia

    INDEX
    Explanations

    cocktail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าประ
    -0.07
    Tambah
    -0.07
     tô
    -0.07
     TIM
    -0.06
     فقط
    -0.06
     Stem
    -0.06
     oblig
    -0.06
    _IMPORTED
    -0.06
     Milan
    -0.06
     targ
    -0.06
    POSITIVE LOGITS
     polarization
    0.07
    828
    0.06
    (features
    0.06
     Documentary
    0.06
    ],
    0.06
     rủi
    0.06
    lower
    0.06
    _SCHEMA
    0.06
    =\
    0.06
     interface
    0.06
    Act Density 0.000%

    No Known Activations