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

    Neuronpedia

    INDEX
    Explanations

    legal references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أنها
    -0.07
    া�
    -0.07
     bb
    -0.07
     villain
    -0.07
    δ
    -0.06
     pa
    -0.06
     removing
    -0.06
     startPos
    -0.06
    rape
    -0.06
    子宫
    -0.06
    POSITIVE LOGITS
    ︕
    0.07
    ��
    0.07
    ::__
    0.07
    ☫
    0.07
    buzz
    0.07
    きっ
    0.07
    мед
    0.07
    ⿃
    0.07
     estable
    0.06
    (edit
    0.06
    Act Density 0.000%

    No Known Activations