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

    Neuronpedia

    INDEX
    Explanations

    Website page code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kt
    -0.07
    rices
    -0.07
    jectives
    -0.06
    项
    -0.06
     beforehand
    -0.06
    یک
    -0.06
     Rams
    -0.06
    çois
    -0.06
    Means
    -0.06
    یدی
    -0.06
    POSITIVE LOGITS
    .getPosition
    0.08
    -metal
    0.07
    _global
    0.07
    .setAlignment
    0.07
    "]))
    0.06
     paní
    0.06
     AttributeError
    0.06
     colle
    0.06
     Nylon
    0.06
     onOptionsItemSelected
    0.06
    Act Density 0.102%

    No Known Activations