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

    Neuronpedia

    INDEX
    Explanations

    Code/programming syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delegate
    -0.06
    バイ
    -0.06
     installations
    -0.06
     ταιν
    -0.06
    .exe
    -0.06
     Cannes
    -0.06
     NATO
    -0.06
    君
    -0.06
    Wednesday
    -0.06
     años
    -0.06
    POSITIVE LOGITS
     master
    0.06
    du
    0.06
     anyone
    0.06
    ū
    0.06
    (sem
    0.06
     taught
    0.06
    /sw
    0.06
    иты
    0.06
    .preventDefault
    0.06
    +lsi
    0.06
    Act Density 0.020%

    No Known Activations