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

    Neuronpedia

    INDEX
    Explanations

    command line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...'
    -0.07
    _measure
    -0.06
    Server
    -0.06
     Bryant
    -0.06
    widgets
    -0.06
    (nullptr
    -0.06
    latent
    -0.06
    EV
    -0.06
    $('
    -0.06
     Specify
    -0.06
    POSITIVE LOGITS
     STRICT
    0.08
     Boxing
    0.08
     impose
    0.07
     перек
    0.07
     kön
    0.06
     VERBOSE
    0.06
    ۶
    0.06
     Developing
    0.06
     چین
    0.06
    .online
    0.06
    Act Density 0.048%

    No Known Activations