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

    Neuronpedia

    INDEX
    Explanations

    weather forecast urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basically
    0.41
    عار
    0.39
     അര
    0.39
    ille
    0.38
    いますが
    0.37
     захи
    0.37
    tender
    0.36
    민국
    0.36
     charges
    0.35
    basically
    0.35
    POSITIVE LOGITS
     kusal
    0.45
     veterinarian
    0.40
     सक्
    0.40
     Barnard
    0.40
    Approximately
    0.39
     Approximately
    0.39
     viewHolder
    0.39
     Mystery
    0.39
     unamb
    0.39
    ází
    0.39
    Act Density 0.003%

    No Known Activations