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

    Neuronpedia

    INDEX
    Explanations

    -z

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    만
    -0.07
    enade
    -0.07
     Arizona
    -0.07
    'er
    -0.07
    ippers
    -0.07
     admit
    -0.07
    ides
    -0.07
    sume
    -0.07
    добав
    -0.07
     verifies
    -0.07
    POSITIVE LOGITS
    oving
    0.07
     ")↵↵
    0.07
     '';↵↵
    0.07
    ：“
    0.07
    )=='
    0.06
     נכונה
    0.06
     //--------------------------------
    0.06
     *);↵
    0.06
     hone
    0.06
    0.06
    Act Density 0.001%

    No Known Activations