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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CUDA
    -0.07
     Parade
    -0.07
     Bottom
    -0.06
    전
    -0.06
    .fxml
    -0.06
     gắn
    -0.06
    _solve
    -0.06
    HOUSE
    -0.06
     demonstrations
    -0.06
    _plane
    -0.06
    POSITIVE LOGITS
     hooks
    0.07
     educating
    0.07
     Fach
    0.06
    _hr
    0.06
    ’:
    0.06
     Siz
    0.06
     hardwood
    0.06
     хв
    0.06
    rnd
    0.06
     """
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations