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

    Neuronpedia

    INDEX
    Explanations

    code, language, grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rit
    -0.07
    τοκ
    -0.07
     essere
    -0.07
     acidic
    -0.06
    ày
    -0.06
     blanco
    -0.06
     cleanse
    -0.06
     fuera
    -0.06
     φω
    -0.06
     Mish
    -0.06
    POSITIVE LOGITS
     málo
    0.07
    ################################################################
    0.06
     seçim
    0.06
    ฆ
    0.06
    ][-
    0.06
     ----------↵
    0.06
    `=
    0.06
    '],↵
    0.06
     unavoidable
    0.06
    �다
    0.06
    Act Density 0.012%

    No Known Activations