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

    Neuronpedia

    INDEX
    Explanations

    fixing/improving things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.87
    enderror
    -0.72
     telling
    -0.71
    expandindo
    -0.69
    DockStyle
    -0.68
    enetrable
    -0.68
    AllAfrica
    -0.68
     Parcelable
    -0.67
    EDEFAULT
    -0.67
    devamını
    -0.66
    POSITIVE LOGITS
    ed
    0.71
    ize
    0.71
    ly
    0.68
    ie
    0.62
    ist
    0.59
    ized
    0.54
    el
    0.52
    ient
    0.51
    i
    0.51
    ii
    0.48
    Act Density 0.165%

    No Known Activations