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

    Neuronpedia

    INDEX
    Explanations

    philosophical concepts and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vég
    0.48
     quedado
    0.47
     alemán
    0.46
     deutschen
    0.46
     connaître
    0.46
     belladone
    0.45
     derivada
    0.45
     koristiti
    0.45
    भावस्था
    0.45
     deaktiv
    0.45
    POSITIVE LOGITS
    How
    0.61
    Why
    0.50
    Re
    0.47
     How
    0.47
    T
    0.47
    What
    0.46
    R
    0.44
    Butterfly
    0.44
    想
    0.43
    S
    0.43
    Act Density 0.000%

    No Known Activations