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

    Neuronpedia

    INDEX
    Explanations

    exhibiting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仕組み
    0.70
    ジョ
    0.64
    申し込み
    0.61
    𝘥
    0.61
     целью
    0.60
    書いて
    0.59
    джа
    0.59
     руководством
    0.59
    Techn
    0.58
     рассказывает
    0.58
    POSITIVE LOGITS
     exhibit
    1.48
     exhibits
    1.30
     preferentially
    1.29
     exhibiting
    1.26
     exhibited
    1.23
     exhib
    1.08
     weakly
    1.03
     Exhibit
    1.03
     exib
    0.95
     monotonically
    0.94
    Act Density 0.266%

    No Known Activations