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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mapper
    -0.08
     requestOptions
    -0.07
     Mapper
    -0.07
     bipartisan
    -0.07
    agine
    -0.07
     dependency
    -0.06
     security
    -0.06
    -parse
    -0.06
    структор
    -0.06
    まだ
    -0.06
    POSITIVE LOGITS
    ('-
    0.07
    烯
    0.07
    .getEmail
    0.07
    ('?
    0.07
     krótk
    0.07
    首
    0.07
    请你
    0.07
    瘟
    0.07
    ('//
    0.07
    ahl
    0.06
    Act Density 0.005%

    No Known Activations