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

    Neuronpedia

    INDEX
    Explanations

    demo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alnum
    -0.07
    ushima
    -0.07
     meanwhile
    -0.06
    圳
    -0.06
     jedno
    -0.06
     Bin
    -0.06
     уровне
    -0.06
    itures
    -0.06
    婦
    -0.06
    _RECV
    -0.06
    POSITIVE LOGITS
     atrav
    0.07
     quella
    0.06
    aternion
    0.06
     hüküm
    0.06
    icontrol
    0.06
     Twig
    0.06
    .hpp
    0.06
    ML
    0.06
     �
    0.06
     enjo
    0.06
    Act Density 0.012%

    No Known Activations