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

    Neuronpedia

    INDEX
    Explanations

    Titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reſ
    -0.73
    ']):
    -0.72
     ſmall
    -0.71
     ſeveral
    -0.71
     purpoſe
    -0.69
     Diſ
    -0.68
     {}));
    -0.68
    ."));
    -0.68
     myſelf
    -0.68
     Towns
    -0.66
    POSITIVE LOGITS
    men
    0.62
     يتيمه
    0.57
    ління
    0.56
    ArgsConstructor
    0.55
    abetes
    0.55
    hip
    0.53
    spire
    0.51
    spira
    0.50
    hips
    0.49
    roots
    0.49
    Act Density 0.031%

    No Known Activations