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

    Neuronpedia

    INDEX
    Explanations

    change concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seekBar
    0.42
     sue
    0.41
     Jo
    0.40
    རྒྱ
    0.38
    <0xC2>
    0.38
    খ্যা
    0.38
     def
    0.36
     MediaQuery
    0.36
     Sort
    0.36
    adiator
    0.35
    POSITIVE LOGITS
    change
    0.64
    Change
    0.61
     change
    0.60
    conv
    0.58
    Conv
    0.57
     Change
    0.55
    chang
    0.55
    changed
    0.53
     convinced
    0.52
     चेंज
    0.52
    Act Density 0.000%

    No Known Activations