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

    Neuronpedia

    INDEX
    Explanations

    assume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maker
    -0.06
     delightful
    -0.06
    sale
    -0.06
     destroying
    -0.06
     breakfast
    -0.06
     apart
    -0.06
     copyright
    -0.05
     contraseña
    -0.05
     blind
    -0.05
    _TD
    -0.05
    POSITIVE LOGITS
     assume
    0.08
     assumed
    0.07
     رئ
    0.07
    DOT
    0.07
     assumes
    0.07
    ｉ
    0.07
    .toCharArray
    0.07
    .onOptionsItemSelected
    0.07
     UIG
    0.07
     harness
    0.07
    Act Density 0.006%

    No Known Activations