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

    Neuronpedia

    INDEX
    Explanations

    detectors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coach
    -0.08
    Coach
    -0.08
     enforce
    -0.07
    clearfix
    -0.07
    ви
    -0.07
    _view
    -0.07
     omo
    -0.07
     Hogwarts
    -0.07
    .replace
    -0.07
    .insert
    -0.07
    POSITIVE LOGITS
     detectors
    0.14
     sensores
    0.12
    Sensitivity
    0.12
     sensitive
    0.12
     sensitivity
    0.12
     حساس
    0.11
     sensibilidad
    0.11
    ensitive
    0.11
    ensitivity
    0.11
     sensors
    0.10
    Act Density 0.010%

    No Known Activations