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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coronavirus
    -0.07
     ik
    -0.07
     Miller
    -0.07
     Server
    -0.06
    _hello
    -0.06
    (diff
    -0.06
     signatures
    -0.06
    idar
    -0.06
     فناوری
    -0.06
    είου
    -0.06
    POSITIVE LOGITS
    από
    0.07
    )}>↵
    0.07
    จร
    0.06
    .Π
    0.06
     Petsc
    0.06
    uxtap
    0.06
    NÍ
    0.06
     eyeb
    0.06
    '&&
    0.06
    恢
    0.06
    Act Density 0.005%

    No Known Activations