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

    Neuronpedia

    INDEX
    Explanations

    You can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്ര
    0.36
    Cryptography
    0.35
     приходится
    0.35
     Conditioner
    0.35
    PRESENT
    0.34
    ಿಯಾಗಿ
    0.34
     analyser
    0.34
     ciphertext
    0.34
     bha
    0.34
     ფორ
    0.34
    POSITIVE LOGITS
     can
    0.60
     should
    0.60
     may
    0.59
     might
    0.52
     probably
    0.52
     deserve
    0.51
    ell
    0.45
     could
    0.45
     sollte
    0.45
     owe
    0.44
    Act Density 0.034%

    No Known Activations