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

    Neuronpedia

    INDEX
    Explanations

    selecting html elements with selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     college
    0.39
    शिया
    0.39
     এবারের
    0.38
    分の
    0.38
     builtin
    0.38
     pulumi
    0.37
    inergic
    0.35
     husband
    0.35
     طور
    0.34
     superhuman
    0.34
    POSITIVE LOGITS
     '#
    1.10
     "#
    1.02
    "#
    0.93
    :'#
    0.93
    ("#
    0.91
    ('#
    0.90
    ('.
    0.90
     ['.
    0.88
     (".
    0.88
     '.
    0.87
    Act Density 0.012%

    No Known Activations