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

    Neuronpedia

    INDEX
    Explanations

    a [adjective]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.29
     multiplets
    1.13
     subsidiaries
    1.10
     beginnings
    1.01
    療法
    1.01
     suburbs
    1.00
    ই
    0.98
     resumes
    0.95
     sequels
    0.94
     peces
    0.94
    POSITIVE LOGITS
    ie
    1.08
    ic
    1.05
    ing
    1.01
    AR
    1.00
    ной
    0.93
    arbe
    0.89
    മ്പ്
    0.88
    ar
    0.87
    ԁ
    0.86
    ed
    0.86
    Act Density 0.291%

    No Known Activations