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

    Neuronpedia

    INDEX
    Explanations

    descriptive clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喈
    0.62
     ένα
    0.48
     ഇപ്പോൾ
    0.48
    ]::-
    0.47
     אחת
    0.46
     சிலை
    0.46
     ಈಗ
    0.46
    ickým
    0.45
     ያሉ
    0.45
    ických
    0.45
    POSITIVE LOGITS
    sho
    0.57
    to
    0.51
     algal
    0.48
    ids
    0.47
    pop
    0.45
    ser
    0.45
    pe
    0.45
    п
    0.44
    м
    0.44
    в
    0.43
    Act Density 0.002%

    No Known Activations