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

    Neuronpedia

    INDEX
    Explanations

    ideal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     करुन
    0.39
    anele
    0.37
     Dodson
    0.36
    膚
    0.35
    ButtonItem
    0.35
    Indirect
    0.34
     зачем
    0.34
    肤
    0.34
     ಅಪಾಯ
    0.34
     Indirect
    0.33
    POSITIVE LOGITS
     ideal
    2.77
    理想
    2.77
    ideal
    2.61
     идеа
    2.58
     Ideal
    2.53
    Ideal
    2.53
     idéal
    2.36
     ideale
    2.23
     idealized
    2.23
     ideales
    2.13
    Act Density 0.054%

    No Known Activations