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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ann
    -0.07
     Havana
    -0.07
     올
    -0.06
     kiến
    -0.06
     米
    -0.06
     бан
    -0.06
     всех
    -0.06
    ツ
    -0.06
     Rico
    -0.06
     handguns
    -0.06
    POSITIVE LOGITS
     CLOCK
    0.06
     poč
    0.06
    Cors
    0.06
    Gain
    0.06
    silent
    0.06
     Rout
    0.06
    agner
    0.06
    _triangle
    0.06
    �
    0.06
    Act
    0.06
    Act Density 0.051%

    No Known Activations