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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pregnancies
    -0.06
     enfants
    -0.06
     prze
    -0.06
    ��
    -0.06
    想要
    -0.06
    -､
    -0.06
    Дж
    -0.06
    quisa
    -0.06
     randint
    -0.06
     Дж
    -0.06
    POSITIVE LOGITS
    -under
    0.07
     Vill
    0.07
     bestimm
    0.07
     -↵↵
    0.07
    ９
    0.06
    ."
    0.06
     USING
    0.06
     Professional
    0.06
    213
    0.06
    ：“
    0.06
    Act Density 0.000%

    No Known Activations