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

    Neuronpedia

    INDEX
    Explanations

    colors

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icitis
    0.71
     éché
    0.63
     वसूली
    0.63
     Saginaw
    0.62
    癹
    0.61
     микро
    0.59
    釘
    0.59
     Nail
    0.59
    打电话
    0.57
    油脂
    0.57
    POSITIVE LOGITS
     blue
    2.40
     red
    2.36
     yellow
    2.36
     green
    2.27
     gray
    2.26
     grey
    2.23
     brown
    2.16
     reds
    2.15
    yellow
    2.11
     pink
    2.10
    Act Density 0.460%

    No Known Activations