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

    Neuronpedia

    INDEX
    Explanations

    produce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bits
    -0.08
     aptly
    -0.08
     assessing
    -0.08
    .Ar
    -0.08
     examining
    -0.07
     Ar
    -0.07
     rad
    -0.07
     Lessons
    -0.07
     lessons
    -0.07
     studying
    -0.07
    POSITIVE LOGITS
     cra
    0.10
    -los
    0.09
     obedient
    0.08
     только
    0.08
    Spacing
    0.08
     formatted
    0.08
     Только
    0.08
     મોક
    0.08
     sequência
    0.08
    formatted
    0.08
    Act Density 0.025%

    No Known Activations