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

    Neuronpedia

    INDEX
    Explanations

    image assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Joint
    0.45
    octrl
    0.44
    Архі
    0.43
     परिसर
    0.41
     Premises
    0.40
     Joint
    0.40
     Joints
    0.40
     Primeiro
    0.39
    ❃
    0.39
     Иң
    0.39
    POSITIVE LOGITS
    చ్చ
    0.39
    massage
    0.38
    wast
    0.37
    system
    0.37
    THA
    0.36
     calculator
    0.36
    fst
    0.36
    방
    0.35
    ӥ
    0.35
    social
    0.35
    Act Density 0.000%

    No Known Activations