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

    Neuronpedia

    INDEX
    Explanations

    cent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     center
    -0.60
     centers
    -0.59
     CENT
    -0.59
    CENTER
    -0.58
    centers
    -0.57
    center
    -0.53
     CENTER
    -0.52
     cent
    -0.51
     Centers
    -0.50
    Center
    -0.49
    POSITIVE LOGITS
     typelib
    0.85
     favourable
    0.75
     unfavourable
    0.74
     apologised
    0.73
     favourably
    0.73
     moulds
    0.72
     favour
    0.71
     localised
    0.71
     незавершена
    0.71
     recognised
    0.70
    Act Density 0.081%

    No Known Activations