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

    Neuronpedia

    INDEX
    Explanations

    planning and operational contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.54
    kaart
    0.50
    ad
    0.49
    cek
    0.48
    quita
    0.48
    yel
    0.47
    otro
    0.46
    arán
    0.46
    orong
    0.46
    uslar
    0.45
    POSITIVE LOGITS
     trabalhadores
    0.54
     bushes
    0.52
    𝐊
    0.49
     paintball
    0.49
    Level
    0.49
     timezone
    0.48
    𝐅
    0.48
     banknotes
    0.47
     troops
    0.46
     肩
    0.45
    Act Density 0.000%

    No Known Activations