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

    Neuronpedia

    INDEX
    Explanations

    ellipses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ывать
    -0.07
    \uff
    -0.07
     Hor
    -0.06
     明
    -0.06
    iam
    -0.06
     pán
    -0.06
     recordings
    -0.06
    iae
    -0.06
     anlam
    -0.06
     velmi
    -0.06
    POSITIVE LOGITS
    Image
    0.06
     Aluminum
    0.06
    EXEC
    0.06
    ibrary
    0.06
    _fl
    0.06
    ー
    0.06
     엄마
    0.06
    .NO
    0.06
     -
    0.06
     muzzle
    0.06
    Act Density 0.004%

    No Known Activations