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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    -Free
    -0.07
    career
    -0.07
    lan
    -0.06
     bahwa
    -0.06
    (frames
    -0.06
     propag
    -0.06
     dni
    -0.06
     propagation
    -0.06
    <cv
    -0.06
    POSITIVE LOGITS
    数学
    0.06
    caler
    0.06
                       ↵
    0.06
    룡
    0.06
     splice
    0.06
     ид
    0.06
     getRandom
    0.06
     चर
    0.06
     PartialEq
    0.06
     посл
    0.06
    Act Density 0.004%

    No Known Activations