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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stick
    -0.07
    íveis
    -0.06
    子供
    -0.06
    Tester
    -0.06
     سرو
    -0.06
     temples
    -0.06
     Gwen
    -0.06
     deps
    -0.06
    never
    -0.06
     petit
    -0.06
    POSITIVE LOGITS
     parts
    0.07
    .StringVar
    0.06
    (remote
    0.06
    .IC
    0.06
     ");↵↵
    0.06
    ！」↵↵
    0.06
    .Pull
    0.06
    )."
    0.06
    .Ş
    0.05
    ).
    0.05
    Act Density 0.033%

    No Known Activations