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

    Neuronpedia

    INDEX
    Explanations

    biological brain simulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿಕೊಂಡ
    0.44
    StrTo
    0.42
    Quan
    0.41
     Quan
    0.40
    dd
    0.40
     pivots
    0.39
     ಪ್ರಾ
    0.39
    Alo
    0.38
    wp
    0.37
     조선
    0.36
    POSITIVE LOGITS
    Bew
    0.51
     Bew
    0.47
     Locking
    0.45
     bew
    0.43
     paura
    0.43
    Fear
    0.43
    データの
    0.43
    グラム
    0.41
     Lovely
    0.41
     Daten
    0.41
    Act Density 0.002%

    No Known Activations