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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reef
    -0.08
    )s
    -0.07
    사이
    -0.07
     turret
    -0.07
     Về
    -0.07
    .ib
    -0.06
    เมตร
    -0.06
    _DIPSETTING
    -0.06
    sequelize
    -0.06
    .moveToFirst
    -0.06
    POSITIVE LOGITS
     Birthday
    0.08
     Jason
    0.08
     Experience
    0.07
    ونا
    0.07
     beta
    0.07
     determine
    0.06
     practice
    0.06
    ّم
    0.06
     Practice
    0.06
    isme
    0.06
    Act Density 0.007%

    No Known Activations