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

    Neuronpedia

    INDEX
    Explanations

    aria- attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hty
    0.38
     Row
    0.36
     Lenn
    0.36
     শহ
    0.36
    ക്കി
    0.36
     Poe
    0.36
     hindsight
    0.35
     সমূহ
    0.35
     Aug
    0.35
     Physik
    0.35
    POSITIVE LOGITS
     controls
    0.54
     controles
    0.52
     controle
    0.46
     control
    0.46
     Controls
    0.46
    controls
    0.45
    Controls
    0.45
     genetically
    0.42
     контроля
    0.42
     контроль
    0.42
    Act Density 0.000%

    No Known Activations