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

    Neuronpedia

    INDEX
    Explanations

    technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrays
    -0.06
     Joanna
    -0.06
    amı
    -0.06
     cof
    -0.06
    attery
    -0.06
     Gow
    -0.06
     whe
    -0.06
    альним
    -0.06
    タン
    -0.06
     iphone
    -0.06
    POSITIVE LOGITS
    ldr
    0.07
    />↵↵
    0.07
    やす
    0.07
    ,data
    0.06
    ，《
    0.06
     Appl
    0.06
     Played
    0.06
    gypt
    0.06
    ながら
    0.06
     Personally
    0.06
    Act Density 0.059%

    No Known Activations