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

    Neuronpedia

    INDEX
    Explanations

    Code characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िध
    -0.07
    .Writer
    -0.07
     sinks
    -0.07
    (include
    -0.07
     Avenue
    -0.07
     CFR
    -0.07
    oric
    -0.06
     inhibited
    -0.06
     IDs
    -0.06
    Tracker
    -0.06
    POSITIVE LOGITS
     sorumlu
    0.06
    ?>"/>↵
    0.06
     Nancy
    0.06
     ослож
    0.06
     misinformation
    0.06
     Müslüman
    0.06
     Moroccan
    0.06
     бороть
    0.05
     jednoduch
    0.05
     Rebecca
    0.05
    Act Density 0.008%

    No Known Activations