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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISK
    -0.08
    еления
    -0.07
    助
    -0.06
     enzym
    -0.06
    ogn
    -0.06
    薦
    -0.06
     blat
    -0.06
     invasive
    -0.06
    �
    -0.06
     argparse
    -0.06
    POSITIVE LOGITS
    _ulong
    0.07
     decode
    0.06
    転
    0.06
    เพราะ
    0.06
    ocale
    0.06
     newNode
    0.06
     durumda
    0.06
    .play
    0.06
    .metro
    0.06
    .lo
    0.06
    Act Density 0.005%

    No Known Activations