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

    Neuronpedia

    INDEX
    Explanations

    However

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狞
    -0.08
    _login
    -0.07
    pedido
    -0.07
    здание
    -0.06
    .oauth
    -0.06
    맷
    -0.06
    .twitter
    -0.06
    战斗
    -0.06
    搞好
    -0.06
    bourne
    -0.06
    POSITIVE LOGITS
    ystals
    0.07
    既可以
    0.07
     Viol
    0.07
     vessel
    0.07
     clarify
    0.07
    يسر
    0.07
     USE
    0.07
     pathways
    0.07
    .Windows
    0.07
     declarations
    0.06
    Act Density 0.048%

    No Known Activations