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

    Neuronpedia

    INDEX
    Explanations

    general description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    -1.92
     changed
    -1.81
     because
    -1.79
     before
    -1.75
     started
    -1.70
     increase
    -1.68
     changes
    -1.63
     reduces
    -1.62
     when
    -1.62
     found
    -1.61
    POSITIVE LOGITS
     teater
    2.00
    extremely
    1.96
     kristal
    1.92
    theres
    1.88
     kalender
    1.81
    Accordingly
    1.78
     katalog
    1.78
     hunde
    1.77
     superbes
    1.77
    basically
    1.76
    Act Density 0.537%

    No Known Activations