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

    Neuronpedia

    INDEX
    Explanations

    ** formatting or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adiabatic
    0.49
    Calculation
    0.48
    0.48
     者
    0.47
    manip
    0.47
    Manipulation
    0.47
    Fraction
    0.46
     żad
    0.46
    ImgBoard
    0.46
     wnios
    0.46
    POSITIVE LOGITS
     Camp
    0.52
     Watt
    0.47
     National
    0.46
     America
    0.46
     is
    0.46
     На
    0.46
     re
    0.46
     Tag
    0.45
     Land
    0.45
     on
    0.44
    Act Density 0.000%

    No Known Activations