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

    Neuronpedia

    INDEX
    Explanations

    fill in the blank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abhid
    0.36
     oeuvre
    0.36
     слай
    0.35
     archi
    0.34
     BEAUT
    0.33
     curviliné
    0.32
     Waugh
    0.32
     genoemd
    0.32
     Arzt
    0.32
     स्लाइड
    0.31
    POSITIVE LOGITS
    ️
    0.33
    "
    0.31
    0.29
    the
    0.29
    ﺯ
    0.29
    ện
    0.28
     cruel
    0.28
    ин
    0.27
     mist
    0.26
     மட்டுமே
    0.26
    Act Density 0.015%

    No Known Activations