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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Banana
    -0.07
     clearing
    -0.07
    何か
    -0.06
    私が
    -0.06
     reunited
    -0.06
     Sampling
    -0.06
     Vermont
    -0.06
    ibble
    -0.06
    ทำความ
    -0.06
     peanut
    -0.06
    POSITIVE LOGITS
    גברים
    0.07
    каз
    0.06
    унк
    0.06
    梃
    0.06
    ymb
    0.06
    實
    0.06
    造成
    0.06
    개
    0.06
    .DIS
    0.06
    _EXPECT
    0.06
    Act Density 0.009%

    No Known Activations