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

    Neuronpedia

    INDEX
    Explanations

    type field values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     メール
    0.42
     Jol
    0.41
     écologique
    0.41
    蝠
    0.41
     caractér
    0.40
    надцати
    0.39
     crée
    0.39
    浏
    0.38
    apadani
    0.37
     tě
    0.37
    POSITIVE LOGITS
     perfect
    0.44
    ablemente
    0.36
     interesting
    0.36
    disk
    0.36
     imperfect
    0.36
    disc
    0.36
    tej
    0.35
    number
    0.35
    perfect
    0.35
    Happ
    0.35
    Act Density 0.005%

    No Known Activations