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

    Neuronpedia

    INDEX
    Explanations

    not constitute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     down
    0.91
     half
    0.76
     hundreds
    0.74
    ,
    0.71
     human
    0.71
     rates
    0.70
     hundred
    0.70
     (
    0.69
    .
    0.68
     moves
    0.68
    POSITIVE LOGITS
    countery
    0.78
    ()}.
    0.78
    <unused84>
    0.77
    ጺ
    0.76
    0.76
     conteú
    0.76
    slideDuplicate
    0.75
     cultivés
    0.75
     işlemi
    0.74
    hwnd
    0.74
    Act Density 0.015%

    No Known Activations