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

    Neuronpedia

    INDEX
    Explanations

    computer and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    op
    0.45
     TWO
    0.41
     BOX
    0.41
     views
    0.40
     EOF
    0.40
    add
    0.40
    b
    0.40
     alters
    0.40
    ;
    0.40
     skewers
    0.39
    POSITIVE LOGITS
    遢
    0.49
     работал
    0.46
    ᅡ
    0.45
     работают
    0.44
    <0xAA>
    0.44
    ᆞ
    0.44
     सैलरी
    0.43
     बेरोजगार
    0.43
    Uttar
    0.43
     зовут
    0.42
    Act Density 0.000%

    No Known Activations