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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ConsoleColor
    -0.07
    佩
    -0.07
    寄
    -0.07
    	cc
    -0.06
    琳
    -0.06
    ffer
    -0.06
    点
    -0.06
     кла
    -0.06
     htons
    -0.06
     quint
    -0.06
    POSITIVE LOGITS
    ickými
    0.07
    Aw
    0.07
    ая
    0.06
    missible
    0.06
     installment
    0.06
    ثر
    0.06
     zaw
    0.06
    нее
    0.06
     ordinarily
    0.06
     innovative
    0.06
    Act Density 0.007%

    No Known Activations