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

    Neuronpedia

    INDEX
    Explanations

    saved in backup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    マータイヤ
    0.47
    ظيم
    0.45
    ਲੀ
    0.44
    フォルト
    0.43
    unkt
    0.43
    Asc
    0.42
    čiti
    0.42
    িয়
    0.42
    itemconfig
    0.42
    ですから
    0.41
    POSITIVE LOGITS
     prostitution
    0.49
     har
    0.48
     side
    0.47
     The
    0.47
     Po
    0.47
     più
    0.47
     STOP
    0.47
     tuna
    0.46
     Pop
    0.46
     je
    0.46
    Act Density 0.003%

    No Known Activations