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

    Neuronpedia

    INDEX
    Explanations

    explanations using "hence"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ِك
    -0.07
    ılan
    -0.07
     germ
    -0.07
    ヘ
    -0.07
    etAddress
    -0.07
     beats
    -0.06
     untuk
    -0.06
     yak
    -0.06
     phá
    -0.06
     Freem
    -0.06
    POSITIVE LOGITS
    .]
    0.08
     Sug
    0.07
    Inicial
    0.06
     avere
    0.06
    ***/↵
    0.06
    CodeAt
    0.06
    PART
    0.06
    ampions
    0.06
     USED
    0.06
    公里
    0.06
    Act Density 0.242%

    No Known Activations