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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ring
    -0.07
     virtual
    -0.06
     merges
    -0.06
    translation
    -0.06
     NS
    -0.06
    ("${
    -0.06
    students
    -0.06
    _statement
    -0.06
    .Nodes
    -0.06
    arella
    -0.06
    POSITIVE LOGITS
    ็นพ
    0.07
     состояние
    0.07
     Madagascar
    0.07
     phút
    0.06
     출
    0.06
     enslaved
    0.06
    //↵↵↵
    0.06
     выс
    0.06
     assassination
    0.06
    _RGBA
    0.06
    Act Density 0.000%

    No Known Activations