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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.69
     myſelf
    -0.64
    ſelf
    -0.63
    ConstraintMaker
    -0.62
     AppColors
    -0.59
    <?
    -0.58
     adentro
    -0.58
     cauſe
    -0.57
     scorso
    -0.56
    ](#
    -0.54
    POSITIVE LOGITS
     up
    1.12
     Up
    0.84
    up
    0.82
    Up
    0.76
     together
    0.66
     Together
    0.66
    Together
    0.65
    ClientSize
    0.64
     upp
    0.57
    together
    0.57
    Act Density 0.021%

    No Known Activations