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

    Neuronpedia

    INDEX
    Explanations

    fulfill one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prescriptive
    0.54
    or
    0.52
    d
    0.47
    DX
    0.45
    baked
    0.45
    nikov
    0.44
     निजा
    0.44
    ethash
    0.43
    y
    0.43
    variety
    0.42
    POSITIVE LOGITS
     viaggio
    0.50
    舰
    0.48
    ᱧ
    0.48
     resumen
    0.47
    ႅ
    0.47
     marchio
    0.46
     apoyo
    0.46
     término
    0.46
     setTo
    0.46
     apoio
    0.44
    Act Density 0.001%

    No Known Activations