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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilis
    -0.07
     له
    -0.07
     Finnish
    -0.07
    ész
    -0.06
     mı
    -0.06
    French
    -0.06
     aides
    -0.06
    άζ
    -0.06
    iba
    -0.06
     mối
    -0.06
    POSITIVE LOGITS
    ificados
    0.07
    .floor
    0.06
     wardrobe
    0.06
    )return
    0.06
    Tp
    0.06
     twitch
    0.06
    attribute
    0.06
     Cipher
    0.06
     adversity
    0.06
    淡
    0.06
    Act Density 0.105%

    No Known Activations