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

    Neuronpedia

    INDEX
    Explanations

    abuse or use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odd
    -0.06
    ada
    -0.06
     ortak
    -0.06
     carrera
    -0.06
    .modal
    -0.06
     svat
    -0.06
     Eggs
    -0.06
     asset
    -0.06
     formas
    -0.06
     hora
    -0.05
    POSITIVE LOGITS
     abuse
    0.11
     Abuse
    0.10
     review
    0.09
     abused
    0.08
     abusing
    0.08
    بي
    0.07
     nghiên
    0.07
     трен
    0.07
    _U
    0.07
    baugh
    0.07
    Act Density 0.006%

    No Known Activations