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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gas
    -0.08
     Dubai
    -0.08
    뻑
    -0.07
    ‛
    -0.07
    eland
    -0.07
    겊
    -0.07
     Bonus
    -0.07
    ῑ
    -0.07
    __()
    -0.07
    氣
    -0.06
    POSITIVE LOGITS
     prescriptions
    0.08
    -project
    0.08
    Normals
    0.08
     basePath
    0.08
    任何
    0.08
    Groups
    0.07
     feminine
    0.07
     incarn
    0.07
     hazards
    0.07
     strat
    0.07
    Act Density 0.015%

    No Known Activations