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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oriously
    -0.06
     puss
    -0.06
    곳
    -0.06
    ายน
    -0.06
     vision
    -0.06
    Release
    -0.06
     MutableList
    -0.06
     dumpsters
    -0.06
    _simps
    -0.06
    .Path
    -0.06
    POSITIVE LOGITS
    _FB
    0.07
     Authenticate
    0.06
     ul
    0.06
     eax
    0.06
     intended
    0.06
    /class
    0.06
     издел
    0.06
    ोषण
    0.06
    �
    0.06
    ':{'
    0.06
    Act Density 0.002%

    No Known Activations