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

    Neuronpedia

    INDEX
    Explanations

    Phoenix Project names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     २०२२
    0.44
     Figma
    0.43
     hyperparameters
    0.42
     ২০২২
    0.42
    二维码
    0.41
    镞
    0.41
     investimentos
    0.40
     Connor
    0.39
     Canva
    0.38
     androidTest
    0.38
    POSITIVE LOGITS
     ২০০
    0.43
     Phoenix
    0.40
    Atlanta
    0.40
    Phoenix
    0.39
     ২০১১
    0.39
     Lid
    0.38
     २००
    0.38
    ându
    0.38
     남아
    0.38
     ۲۰۰
    0.37
    Act Density 0.001%

    No Known Activations