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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ne
    -0.06
    -guid
    -0.06
    _running
    -0.06
    cluster
    -0.06
    ndl
    -0.06
     triangular
    -0.06
    欲望
    -0.06
     triangles
    -0.06
    -0.06
    $user
    -0.06
    POSITIVE LOGITS
     method
    0.11
     methods
    0.10
    舶
    0.08
     DEF
    0.08
    さまざま
    0.08
     Farage
    0.07
     biện
    0.07
    浰
    0.07
    泽连斯基
    0.07
    Fig
    0.07
    Act Density 0.089%

    No Known Activations