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

    Neuronpedia

    INDEX
    Explanations

    disabilities and health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .emp
    -0.07
     Iceland
    -0.07
     nm
    -0.06
    tog
    -0.06
     tertiary
    -0.06
     Glass
    -0.06
    ylv
    -0.06
     BMW
    -0.06
    运
    -0.06
    -car
    -0.06
    POSITIVE LOGITS
     việc
    0.07
    _loop
    0.06
     ENT
    0.06
     krás
    0.06
    ificados
    0.06
    (endpoint
    0.06
     bás
    0.06
    marvin
    0.06
    ––
    0.06
    erchant
    0.06
    Act Density 0.030%

    No Known Activations