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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     >=",
    -0.68
    abestanden
    -0.67
    RegistryLite
    -0.65
    RegressionTest
    -0.60
     autant
    -0.59
    iotensin
    -0.57
    ONCE
    -0.54
     ONCE
    -0.52
     stället
    -0.51
     sekali
    -0.51
    POSITIVE LOGITS
     they
    0.84
    DockStyle
    0.66
     it
    0.65
     do
    0.65
     things
    0.60
     previous
    0.59
     many
    0.58
     does
    0.57
     most
    0.57
     preceding
    0.57
    Act Density 0.000%

    No Known Activations