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

    Neuronpedia

    INDEX
    Explanations

    last one standing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bought
    0.40
    garh
    0.39
    Гц
    0.39
    Borrow
    0.39
     Chowdhury
    0.39
     indexRouter
    0.38
    Ꮡ
    0.38
    ৳
    0.38
    ﺤ
    0.38
     CONNECTION
    0.38
    POSITIVE LOGITS
    up
    0.41
    at
    0.41
    ip
    0.40
    udo
    0.40
     young
    0.40
    anes
    0.40
    indo
    0.39
    udi
    0.39
    upon
    0.39
    ap
    0.39
    Act Density 0.002%

    No Known Activations