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

    Neuronpedia

    INDEX
    Explanations

    semester or edition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tilt
    0.40
    さと
    0.39
    ించ
    0.38
    問
    0.38
     кількість
    0.38
    一提
    0.38
    ції
    0.38
    莎
    0.38
     Wong
    0.37
    Button
    0.36
    POSITIVE LOGITS
     asesor
    0.45
     aprend
    0.44
     serem
    0.44
    ulfillment
    0.44
     varias
    0.43
     acom
    0.43
     reproducible
    0.41
     semester
    0.41
     obstáculos
    0.41
     intern
    0.41
    Act Density 0.001%

    No Known Activations