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

    Neuronpedia

    INDEX
    Explanations

    Predominance of "horizontal"horizontal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horizontal
    -0.92
     Horizontal
    -0.89
    Horizontal
    -0.82
    horizontal
    -0.82
     horizont
    -0.70
     horizontally
    -0.69
     orizz
    -0.65
    ServletConfig
    -0.65
    main
    -0.63
     verticale
    -0.63
    POSITIVE LOGITS
    PerformLayout
    0.59
    nezeu
    0.54
    naire
    0.53
     reductions
    0.52
    bitur
    0.52
    Phas
    0.51
     Redu
    0.50
    marily
    0.50
    aturing
    0.50
     phase
    0.49
    Act Density 0.058%

    No Known Activations