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

    Neuronpedia

    INDEX
    Explanations

    can could

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .jdesktop
    -0.07
    込み
    -0.07
     �
    -0.07
    Intro
    -0.07
    :');↵
    -0.06
     Autodesk
    -0.06
    Salary
    -0.06
     налог
    -0.06
     viel
    -0.06
    ější
    -0.06
    POSITIVE LOGITS
     honestly
    0.07
     kitten
    0.07
     involvement
    0.06
    ilst
    0.06
     depended
    0.06
    .fml
    0.06
    iros
    0.06
    .TryParse
    0.06
    заб
    0.06
     возможность
    0.06
    Act Density 0.131%

    No Known Activations