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

    Neuronpedia

    INDEX
    Explanations

    with stress or physical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    noon
    0.38
     Ia
    0.38
    ?
    0.37
     sta
    0.37
     ያ
    0.37
    are
    0.36
     -
    0.36
     but
    0.36
     families
    0.35
    is
    0.35
    POSITIVE LOGITS
     químico
    0.48
     índice
    0.46
    glRaster
    0.46
    ിച്ചത്
    0.46
    InputCommand
    0.45
     complejos
    0.44
     tranquillity
    0.44
     விதி
    0.43
    ᕈ
    0.43
    ೋದ
    0.43
    Act Density 0.000%

    No Known Activations