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

    Neuronpedia

    INDEX
    Explanations

    pluralization/possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OMITTED
    -0.50
     there
    -0.41
     become
    -0.41
    agrid
    -0.41
     such
    -0.40
     tijd
    -0.40
     called
    -0.40
     held
    -0.39
     moved
    -0.39
    arraycopy
    -0.39
    POSITIVE LOGITS
    AutoScaleMode
    0.83
     seals
    0.72
     attachments
    0.70
    FieldBuilder
    0.69
     coaches
    0.68
     puns
    0.67
     cartoons
    0.67
     bosses
    0.66
     prospects
    0.66
     recoveries
    0.66
    Act Density 0.006%

    No Known Activations