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

    Neuronpedia

    INDEX
    Explanations

    re this Settings Power degree sequence Famous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.50
     일으
    0.42
    ทั่ว
    0.40
    თან
    0.40
     utenti
    0.40
     lograr
    0.39
    ടുത
    0.39
    nici
    0.39
     السبب
    0.39
    EDEN
    0.39
    POSITIVE LOGITS
     nantinya
    0.43
    PAPER
    0.42
     đô
    0.41
    ठन
    0.40
    রাষ্ট
    0.40
    炇
    0.40
    ợp
    0.39
     PAPER
    0.39
    克力
    0.38
     geleden
    0.38
    Act Density 0.000%

    No Known Activations