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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    僕
    -0.07
    Spanish
    -0.07
     JSON
    -0.06
    盖
    -0.06
    .Values
    -0.06
    �
    -0.06
    280
    -0.06
    .users
    -0.06
    енти
    -0.06
    _modules
    -0.06
    POSITIVE LOGITS
     moy
    0.07
    клад
    0.07
    DockControl
    0.07
    боратор
    0.06
    оратив
    0.06
    kte
    0.06
     authenticate
    0.06
     RuntimeMethod
    0.06
    /lgpl
    0.06
     quantidade
    0.06
    Act Density 0.026%

    No Known Activations