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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "name
    -0.06
    _modules
    -0.06
    νομα
    -0.06
    �
    -0.06
     ################
    -0.06
     cheering
    -0.06
    орот
    -0.06
    روز
    -0.06
    .ef
    -0.06
     kron
    -0.06
    POSITIVE LOGITS
    Using
    0.08
     Using
    0.07
    Use
    0.07
     мови
    0.06
     domác
    0.06
     Con
    0.06
     Din
    0.06
    _USE
    0.06
     using
    0.06
     Submit
    0.06
    Act Density 0.012%

    No Known Activations