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
     tròn
    -0.06
     경우
    -0.06
     Manson
    -0.06
     수가
    -0.06
     "&
    -0.06
     ambassador
    -0.06
    Hp
    -0.06
     pays
    -0.06
     Colour
    -0.06
    timeline
    -0.06
    POSITIVE LOGITS
     NEGLIGENCE
    0.07
     Tribunal
    0.07
    JKLM
    0.06
     polar
    0.06
    互联网
    0.06
    ENCHMARK
    0.06
     onlar
    0.06
    _LA
    0.06
    チャ
    0.06
    -present
    0.06
    Act Density 0.029%

    No Known Activations