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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Has
    -0.07
     Has
    -0.07
     neither
    -0.06
    _linear
    -0.06
     verv
    -0.06
    Finish
    -0.06
    .lesson
    -0.06
     Lies
    -0.06
    403
    -0.06
    _dd
    -0.06
    POSITIVE LOGITS
     frag
    0.07
     değerlendir
    0.06
    _SHADER
    0.06
    -upload
    0.06
     Functor
    0.06
    [np
    0.06
    (prediction
    0.06
    щик
    0.06
    .xxx
    0.06
     hastalık
    0.06
    Act Density 0.024%

    No Known Activations