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

    Neuronpedia

    INDEX
    Explanations

    the power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    0.55
    ي
    0.54
     vajj
    0.51
     azione
    0.50
     centrales
    0.50
     azienda
    0.50
     secuencia
    0.49
     étend
    0.49
     ampio
    0.48
    zovaniyu
    0.48
    POSITIVE LOGITS
     Board
    0.47
    are
    0.46
     beberapa
    0.44
     $
    0.43
     pew
    0.43
     الله
    0.42
     شود
    0.42
     سوال
    0.42
     Found
    0.42
     Tree
    0.42
    Act Density 0.000%

    No Known Activations