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

    Neuronpedia

    INDEX
    Explanations

    of/about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .repo
    -0.08
    越是
    -0.07
    分钟后
    -0.07
    💑
    -0.07
    そのため
    -0.07
     mdl
    -0.07
    쥐
    -0.07
    pname
    -0.07
    时许
    -0.07
     Sonic
    -0.07
    POSITIVE LOGITS
    ᥰ
    0.07
    allo
    0.07
    导
    0.07
     Picture
    0.07
     Stern
    0.06
    Solid
    0.06
    𬍤
    0.06
     Scores
    0.06
    ам
    0.06
     Komm
    0.06
    Act Density 0.058%

    No Known Activations