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

    Neuronpedia

    INDEX
    Explanations

    AS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ["_
    -0.07
     master
    -0.07
    rypted
    -0.07
     oldValue
    -0.07
    ret
    -0.06
    attempt
    -0.06
    絕
    -0.06
    虺
    -0.06
    ệnh
    -0.06
    Ĭ
    -0.06
    POSITIVE LOGITS
     должно
    0.08
     shall
    0.08
    popup
    0.07
    onna
    0.07
     hoje
    0.07
     Buf
    0.07
    MUX
    0.07
    Four
    0.07
    (bg
    0.07
     Widget
    0.07
    Act Density 0.001%

    No Known Activations