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

    Neuronpedia

    INDEX
    Explanations

    html and javascript interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⇣
    0.35
    绺
    0.34
    ᥣ
    0.33
    髅
    0.31
     necesariamente
    0.30
    峎
    0.30
     Lorentzian
    0.30
    疳
    0.30
     Chirurgien
    0.29
     profinite
    0.29
    POSITIVE LOGITS
    s
    0.32
    n
    0.31
    N
    0.31
    M
    0.30
    im
    0.30
    P
    0.30
    ↵
    0.29
    try
    0.29
     __
    0.29
    __
    0.28
    Act Density 0.001%

    No Known Activations