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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Back
    -0.08
    ὔ
    -0.07
     เม
    -0.07
    מניע
    -0.07
     البي
    -0.07
    )size
    -0.07
    Ế
    -0.07
    _FORWARD
    -0.07
    ebb
    -0.07
     divided
    -0.07
    POSITIVE LOGITS
    writer
    0.08
    融入
    0.07
    Sab
    0.06
    `,↵
    0.06
    |\
    0.06
     overwhelm
    0.06
     refreshed
    0.06
    陪伴
    0.06
    air
    0.06
     A
    0.06
    Act Density 0.017%

    No Known Activations