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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    稗
    -0.08
     �
    -0.07
    㧬
    -0.07
    咽喉
    -0.07
    _$
    -0.07
     sick
    -0.07
     Donovan
    -0.07
    삔
    -0.07
    _Product
    -0.07
     UART
    -0.07
    POSITIVE LOGITS
    人も
    0.08
     SWITCH
    0.07
    开
    0.07
    走了
    0.07
    gie
    0.07
     deserve
    0.07
    用微信扫
    0.07
    ники
    0.07
    更是
    0.06
    errorMessage
    0.06
    Act Density 0.000%

    No Known Activations