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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     систем
    -0.08
    poses
    -0.06
    ẵng
    -0.06
     Hiện
    -0.06
    lı
    -0.06
     infections
    -0.06
    prit
    -0.06
     reducers
    -0.06
    577
    -0.06
     pratic
    -0.06
    POSITIVE LOGITS
     STL
    0.06
    _SCHEMA
    0.06
    SmartPointer
    0.06
    :I
    0.06
    ，您
    0.06
     Regional
    0.06
     Oh
    0.06
     entertained
    0.06
    .bytes
    0.06
     verse
    0.06
    Act Density 0.001%

    No Known Activations