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

    Neuronpedia

    INDEX
    Explanations

    exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Asked
    -0.07
    ᡡ
    -0.07
    ᥖ
    -0.07
    Democrats
    -0.06
    >Status
    -0.06
     startDate
    -0.06
    aurant
    -0.06
    防守
    -0.06
     لكل
    -0.06
    ROWSER
    -0.06
    POSITIVE LOGITS
     Nonetheless
    0.09
     aggregated
    0.07
    毯
    0.07
    殖
    0.07
    cdecl
    0.07
    .proc
    0.07
    ⊇
    0.07
    (ci
    0.07
     "",
↵
    0.07
    し
    0.07
    Act Density 0.014%

    No Known Activations