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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specific
    -0.07
     movement
    -0.07
    180
    -0.07
    162
    -0.07
     positively
    -0.07
    mediately
    -0.06
    World
    -0.06
     ما
    -0.06
     начале
    -0.06
     Dry
    -0.06
    POSITIVE LOGITS
    -reviewed
    0.07
    .dataSource
    0.05
     *[
    0.05
     ζ
    0.05
     elong
    0.05
     حکوم
    0.05
     --↵
    0.05
     nicer
    0.05
     FITNESS
    0.05
     Unix
    0.05
    Act Density 0.159%

    No Known Activations