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

    Neuronpedia

    INDEX
    Explanations

    words and phrases for locations, place, or description of object or action.

    oai_token-act-pair · gemini-2.0-flash

    middle, center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     middle
    -1.02
     centre
    -0.93
    middle
    -0.91
     center
    -0.90
    centre
    -0.85
     centro
    -0.82
    center
    -0.79
     MIDDLE
    -0.79
     centres
    -0.79
    Centers
    -0.78
    POSITIVE LOGITS
    WithTag
    0.53
    tagHelper
    0.52
    tonsoft
    0.50
     microfibra
    0.48
    rival
    0.48
     energy
    0.47
    氓
    0.46
    bewerken
    0.46
    orsch
    0.45
     arras
    0.45
    Act Density 32.241%

    No Known Activations