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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mu
    -0.07
     volunteered
    -0.06
    _ter
    -0.06
     Victor
    -0.06
    <std
    -0.06
     Holl
    -0.06
    ัฐ
    -0.06
    γκ
    -0.06
    τεί
    -0.06
    ntp
    -0.06
    POSITIVE LOGITS
     ألمان
    0.07
     Robotics
    0.07
     Designer
    0.06
     të
    0.06
    .DATE
    0.06
    })"↵
    0.06
    .setHeader
    0.06
     cé
    0.06
    ]}↵
    0.06
    야
    0.06
    Act Density 0.027%

    No Known Activations