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

    Neuronpedia

    INDEX
    Explanations

    full names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chromosome
    0.54
    Annie
    0.53
    Elizabeth
    0.51
    এবং
    0.49
    <unused565>
    0.48
    Arthur
    0.47
    自己的
    0.47
    编译
    0.47
     调用
    0.47
    的名字
    0.47
    POSITIVE LOGITS
     KPIs
    0.53
     impactful
    0.51
     stagnant
    0.50
     lensing
    0.48
     string
    0.47
     sliding
    0.47
     warping
    0.46
     per
    0.46
     barriers
    0.46
     tailored
    0.45
    Act Density 0.026%

    No Known Activations