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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {}↵↵
    -0.07
    าธ
    -0.07
    ",
↵
    -0.06
     frameborder
    -0.06
    '";
↵
    -0.06
     говорить
    -0.06
     волод
    -0.06
     gaat
    -0.06
    lsx
    -0.06
     mejorar
    -0.06
    POSITIVE LOGITS
     lock
    0.07
     multi
    0.07
     Christine
    0.06
     testified
    0.06
     chickens
    0.06
    .ec
    0.06
    Craig
    0.06
    -phase
    0.06
    Pre
    0.06
     Anchor
    0.06
    Act Density 0.000%

    No Known Activations