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

    Neuronpedia

    INDEX
    Explanations

    with no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gaining
    0.41
     getting
    0.40
    ্পর্শ
    0.37
    establishing
    0.37
     feel
    0.36
     establishing
    0.36
     joten
    0.36
    ኮ
    0.36
     achieving
    0.36
     technologies
    0.35
    POSITIVE LOGITS
     no
    0.55
    一個
    0.50
     zwei
    0.48
     één
    0.47
     geen
    0.46
     nessun
    0.45
     minimal
    0.45
     hiçbir
    0.45
     två
    0.43
     কোনো
    0.43
    Act Density 0.140%

    No Known Activations