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

    Neuronpedia

    INDEX
    Explanations

    programming dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bases
    -0.07
     seemed
    -0.06
     rulings
    -0.06
     parody
    -0.06
     rotations
    -0.06
    consistent
    -0.06
     respectful
    -0.06
    .postValue
    -0.06
     lact
    -0.06
     основі
    -0.06
    POSITIVE LOGITS
    .Documents
    0.07
    兰
    0.07
    :[[
    0.06
    Mappings
    0.06
    :'
    0.06
     cic
    0.06
    Granted
    0.06
    273
    0.06
    }}{{
    0.06
     :/:
    0.06
    Act Density 0.000%

    No Known Activations