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

    Neuronpedia

    INDEX
    Explanations

    testing code expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    োদয়
    0.43
    liss
    0.39
     دیکھیں
    0.38
     अकाउंट
    0.38
     veditabbo
    0.37
    હો
    0.37
    ര്‍ന്ന
    0.37
     chartered
    0.36
    নীয়
    0.36
     cpt
    0.36
    POSITIVE LOGITS
    »).
    0.45
    ®.
    0.44
    ().
    0.40
     Stall
    0.40
    /).
    0.40
    ('').
    0.39
    ).
    0.39
    ».
    0.38
    \".
    0.38
     широко
    0.38
    Act Density 0.000%

    No Known Activations