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

    Neuronpedia

    INDEX
    Explanations

    talent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sea
    -0.07
     Năm
    -0.07
    erras
    -0.07
     pageNum
    -0.07
    _Act
    -0.07
     Paras
    -0.06
     boyc
    -0.06
     pipes
    -0.06
     ceux
    -0.06
    伙
    -0.06
    POSITIVE LOGITS
    _dimension
    0.07
    _UNITS
    0.06
    nic
    0.06
     :)
    0.06
     connector
    0.06
     неболь
    0.06
     kaliteli
    0.06
    -cn
    0.06
     recipes
    0.06
    zeich
    0.06
    Act Density 0.067%

    No Known Activations