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

    Neuronpedia

    INDEX
    Explanations

    mental health and addiction resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gospel
    0.78
    cell
    0.72
     কারাগারে
    0.70
    deep
    0.70
     Cell
    0.69
    arpur
    0.68
    चूर
    0.68
     cello
    0.67
    trä
    0.67
     cell
    0.67
    POSITIVE LOGITS
     とする
    0.55
    Strategic
    0.53
    Assert
    0.52
    nymi
    0.50
     समझाया
    0.49
    Love
    0.49
     मि
    0.48
    Wearing
    0.48
     Love
    0.48
    攵
    0.48
    Act Density 0.119%

    No Known Activations