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

    Neuronpedia

    INDEX
    Explanations

    smaller/size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     size
    -0.90
     largest
    -0.89
     Size
    -0.83
     sizes
    -0.79
     smaller
    -0.75
     Smaller
    -0.75
    Size
    -0.73
     Sizes
    -0.73
     Large
    -0.72
     large
    -0.72
    POSITIVE LOGITS
    ArgsConstructor
    0.63
    addCriterion
    0.57
    principalTable
    0.54
    prüche
    0.53
    StreetMap
    0.52
    MetaObject
    0.51
     feldspar
    0.49
     menti
    0.49
    
    0.48
     fathoms
    0.48
    Act Density 0.833%

    No Known Activations