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

    Neuronpedia

    INDEX
    Explanations

    Pixar, Nespresso, applicable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abilities
    0.49
    iate
    0.49
    aire
    0.49
    ون
    0.49
    Offering
    0.48
     of
    0.48
    Animal
    0.48
    happ
    0.47
    <unused62>
    0.45
    fall
    0.44
    POSITIVE LOGITS
    दान
    0.49
     svij
    0.46
     kodu
    0.45
     satın
    0.44
    吋
    0.44
     Kata
    0.43
     comput
    0.43
     impoverished
    0.43
    埤
    0.42
     kata
    0.42
    Act Density 0.004%

    No Known Activations