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

    Neuronpedia

    INDEX
    Explanations

    IOR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ヴァ
    -0.07
    	param
    -0.06
    }},
    -0.06
     prendre
    -0.06
    잔
    -0.06
    마
    -0.06
     fet
    -0.06
    Так
    -0.05
     کاربر
    -0.05
    ché
    -0.05
    POSITIVE LOGITS
     emailing
    0.07
     også
    0.07
     cray
    0.07
    .getBytes
    0.07
     getResource
    0.07
     External
    0.07
     Beispiel
    0.07
    ogene
    0.07
    arkan
    0.06
    /system
    0.06
    Act Density 0.016%

    No Known Activations