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

    Neuronpedia

    INDEX
    Explanations

    specific segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Terrible
    0.66
     professionalism
    0.64
     debacle
    0.64
     Cosmology
    0.63
     Alignment
    0.61
     Suppression
    0.61
     春
    0.61
     Nightmare
    0.61
     Bias
    0.61
     Months
    0.60
    POSITIVE LOGITS
     identifiable
    0.67
     single
    0.63
     ______
    0.61
     measurable
    0.60
     _______
    0.60
     discernible
    0.59
    ______
    0.59
     distinguishable
    0.58
    single
    0.57
     finite
    0.56
    Act Density 1.021%

    No Known Activations