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

    Neuronpedia

    INDEX
    Explanations

    basicConfig and config

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataManager
    0.48
     halved
    0.43
     Zimmerman
    0.42
    tbl
    0.42
     gorg
    0.42
     chamber
    0.41
    tki
    0.41
     زیب
    0.41
     heinous
    0.41
    žal
    0.41
    POSITIVE LOGITS
    感じる
    0.44
    த்த
    0.43
    octet
    0.42
    ᱥ
    0.41
     establecidas
    0.40
    Opacity
    0.39
     प्रा
    0.39
    예
    0.38
    DEFAULT
    0.38
    или
    0.38
    Act Density 0.002%

    No Known Activations