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

    Neuronpedia

    INDEX
    Explanations

    NGOs, Linux, temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    এক্স
    0.42
    endTime
    0.40
    inação
    0.39
     diastere
    0.38
     centaines
    0.38
    sqrt
    0.38
    лан
    0.37
     выгод
    0.36
    >");
    0.36
    ligare
    0.36
    POSITIVE LOGITS
     Modern
    0.43
     रूपा
    0.42
     €.
    0.41
     ----
    0.41
     census
    0.39
     Rollins
    0.39
     patterns
    0.39
    に関する
    0.39
     Ön
    0.39
     Gül
    0.39
    Act Density 0.000%

    No Known Activations