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

    Neuronpedia

    INDEX
    Explanations

    icon names and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nomes
    0.44
    めでとう
    0.43
    冷蔵
    0.42
    *****",
    0.40
    ClearedBy
    0.40
    တွေ
    0.40
     ।*
    0.40
     "*****
    0.39
    nbhd
    0.39
     داع
    0.39
    POSITIVE LOGITS
     icon
    0.93
     icono
    0.77
     Icon
    0.74
    图标
    0.73
    アイコン
    0.72
     आइकन
    0.70
    Outline
    0.69
     outline
    0.69
    Icon
    0.67
     circle
    0.66
    Act Density 0.012%

    No Known Activations