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

    Neuronpedia

    INDEX
    Explanations

    several ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Some
    0.57
    Certain
    0.57
    Equipment
    0.54
    H
    0.54
    This
    0.50
    Many
    0.50
    this
    0.49
    Stuff
    0.49
    Z
    0.48
    Work
    0.48
    POSITIVE LOGITS
     interrelated
    0.91
     iterations
    0.90
     instances
    0.89
     different
    0.87
     kinds
    0.86
     versions
    0.82
     types
    0.81
     contexts
    0.81
     dozen
    0.79
     sets
    0.78
    Act Density 1.403%

    No Known Activations