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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nam
    -0.07
    ensive
    -0.07
    راه
    -0.07
     Afterwards
    -0.06
     RTWF
    -0.06
    ARGS
    -0.06
    ολ
    -0.06
    ると
    -0.06
     ตร
    -0.06
     Hải
    -0.06
    POSITIVE LOGITS
     Vintage
    0.07
    .success
    0.07
    ),"
    0.07
    ]")
    0.06
     Logic
    0.06
     sürekli
    0.06
     Café
    0.06
     Package
    0.06
    ?#
    0.06
    .centerY
    0.06
    Act Density 0.000%

    No Known Activations