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

    Neuronpedia

    INDEX
    Explanations

    adding options or specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    0.37
    clubs
    0.36
     ([
    0.35
    跟你
    0.35
     Clubs
    0.35
     [$
    0.35
    клу
    0.34
    hepat
    0.34
    unus
    0.34
    hely
    0.33
    POSITIVE LOGITS
     lãi
    0.39
    甫
    0.38
     آش
    0.37
    ceff
    0.37
     lmao
    0.37
     óleo
    0.37
    ᥒ
    0.37
     pled
    0.36
     decreased
    0.36
    ාවක්
    0.36
    Act Density 0.001%

    No Known Activations