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

    Neuronpedia

    INDEX
    Explanations

    Mag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    variables
    -0.07
    .yml
    -0.07
     Populate
    -0.06
     joking
    -0.06
    ãi
    -0.06
     segments
    -0.06
     σαν
    -0.06
    arrow
    -0.06
     incremental
    -0.06
     antlr
    -0.06
    POSITIVE LOGITS
    .feedback
    0.08
    Mag
    0.07
     Mag
    0.07
    AG
    0.07
    /gl
    0.07
    τύ
    0.07
     аг
    0.07
    TURE
    0.07
    62
    0.07
    (tex
    0.07
    Act Density 0.006%

    No Known Activations