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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zoo
    -0.08
     cuck
    -0.08
    .websocket
    -0.08
     đuổi
    -0.07
    \Controller
    -0.07
     webinar
    -0.07
     Docker
    -0.07
     virtual
    -0.07
     Zoo
    -0.07
    <c
    -0.07
    POSITIVE LOGITS
     '">'
    0.09
     metall
    0.08
    entials
    0.08
    _portal
    0.08
     juris
    0.07
    哝
    0.07
    甍
    0.07
     우리의
    0.07
    >());↵↵
    0.07
    옮
    0.07
    Act Density 0.008%

    No Known Activations