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

    Neuronpedia

    INDEX
    Explanations

    Numerical data and ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     при
    -0.07
     praising
    -0.06
     Truman
    -0.06
    .DataTable
    -0.06
     professions
    -0.06
     freezer
    -0.06
     predefined
    -0.06
    _allowed
    -0.06
    霞
    -0.06
     عصر
    -0.06
    POSITIVE LOGITS
     repaint
    0.06
    juries
    0.06
     onChanged
    0.06
    ку
    0.06
    _bed
    0.06
     risks
    0.06
    RT
    0.06
     sampled
    0.06
     quella
    0.06
     mak
    0.06
    Act Density 0.022%

    No Known Activations