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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حمل
    -0.07
    Sur
    -0.06
    罪
    -0.06
     tijd
    -0.06
     非
    -0.06
     =
↵
    -0.06
     Hàn
    -0.06
     sur
    -0.06
    orrent
    -0.06
     warp
    -0.06
    POSITIVE LOGITS
     Johnny
    0.06
    Exports
    0.06
     Forbes
    0.06
    -loving
    0.06
    pon
    0.06
    abil
    0.06
     canadian
    0.06
    atab
    0.06
    LF
    0.06
    ulatory
    0.06
    Act Density 0.000%

    No Known Activations