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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ngo
    -0.28
    ç±ģ
    -0.27
    ÄĻk
    -0.26
    大éģĵ
    -0.26
    ught
    -0.25
    bild
    -0.25
    æĭ¼éŁ³
    -0.25
    afx
    -0.24
    zÄĻ
    -0.24
    .pat
    -0.24
    POSITIVE LOGITS
     -,
    0.31
    满äºĨ
    0.29
    ulative
    0.29
     pie
    0.28
     -:
    0.28
    çŁ¥åIJįçļĦ
    0.27
    rical
    0.26
    char
    0.25
     squeezing
    0.25
    åıĭ们
    0.24
    Act Density 0.000%

    No Known Activations