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

    Neuronpedia

    INDEX
    Explanations

    but not impossible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     those
    0.61
     fertilizers
    0.48
    那些
    0.46
     indexes
    0.46
     fertilisers
    0.45
     aquele
    0.44
    Those
    0.43
     ACTIVITIES
    0.42
     Lagrangian
    0.42
     REACTORS
    0.42
    POSITIVE LOGITS
    یی
    0.51
     ১৯
    0.46
    writeFileSync
    0.45
    és
    0.45
    istische
    0.44
    éth
    0.44
    anée
    0.44
    anyang
    0.43
     زیادہ
    0.43
    યા
    0.43
    Act Density 0.007%

    No Known Activations