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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     honestly
    -0.07
    纯
    -0.07
    _POL
    -0.06
     полот
    -0.06
    घ
    -0.06
    <Mesh
    -0.06
    _services
    -0.06
    >v
    -0.06
    \/
    -0.06
     hanya
    -0.06
    POSITIVE LOGITS
    شف
    0.07
    ана
    0.07
     screened
    0.06
     dad
    0.06
     кан
    0.06
     creation
    0.06
     arrang
    0.06
    guarded
    0.06
    任
    0.06
     READY
    0.06
    Act Density 0.007%

    No Known Activations