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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NONE
    -0.07
     Pricing
    -0.07
    erts
    -0.07
     Griffith
    -0.07
    ];
↵
↵
    -0.06
    的是
    -0.06
    دي
    -0.06
     кар
    -0.06
    TO
    -0.06
     condemn
    -0.06
    POSITIVE LOGITS
    稂
    0.07
     Mineral
    0.07
    宄
    0.07
    ilogue
    0.07
    agan
    0.07
    ɫ
    0.07
     dort
    0.07
     apology
    0.07
    (age
    0.07
    �
    0.07
    Act Density 0.083%

    No Known Activations