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

    Neuronpedia

    INDEX
    Explanations

    style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Qualcomm
    -0.07
    -shift
    -0.07
    :d
    -0.07
    verting
    -0.07
    Experts
    -0.07
    Shift
    -0.07
    ilmiştir
    -0.06
     return
    -0.06
    await
    -0.06
    kem
    -0.06
    POSITIVE LOGITS
     Curse
    0.07
     curse
    0.06
    ließ
    0.06
     phenomen
    0.06
    Plate
    0.06
     setUser
    0.06
     bless
    0.06
     시
    0.05
    endent
    0.05
     swinger
    0.05
    Act Density 0.000%

    No Known Activations