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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pier
    -0.07
    -vector
    -0.07
    pi
    -0.06
    erald
    -0.06
    V
    -0.06
    functions
    -0.06
    Roll
    -0.06
    ining
    -0.06
    NV
    -0.06
     Wrapper
    -0.06
    POSITIVE LOGITS
     DAG
    0.07
    .endswith
    0.07
    áct
    0.07
     Begins
    0.06
    ************************************************************************
    0.06
    。不
    0.06
     Yıl
    0.06
    历史
    0.06
    .tolist
    0.06
    �
    0.06
    Act Density 0.094%

    No Known Activations