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

    Neuronpedia

    INDEX
    Explanations

    Underscores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caregivers
    -0.08
     Eva
    -0.08
    Vin
    -0.07
     UI
    -0.07
     Avenue
    -0.07
     melod
    -0.07
    TAG
    -0.07
    UI
    -0.07
     double
    -0.07
     simple
    -0.07
    POSITIVE LOGITS
     Parameters
    0.13
    Attributes
    0.12
     parameters
    0.12
    Parameters
    0.12
    .attributes
    0.12
     параметры
    0.12
     attributes
    0.11
     Characteristics
    0.11
    _parameters
    0.11
    attributes
    0.11
    Act Density 0.039%

    No Known Activations