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

    Neuronpedia

    INDEX
    Explanations

    Include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rophy
    -0.07
     �
    -0.07
    ソ
    -0.06
    iance
    -0.06
    /generated
    -0.06
     باست
    -0.06
     гля
    -0.06
    了
    -0.06
    パン
    -0.05
    确认
    -0.05
    POSITIVE LOGITS
    AMI
    0.07
     typeof
    0.07
    .random
    0.06
     hoạt
    0.06
     Lincoln
    0.06
     nữ
    0.06
     tôn
    0.06
     suprem
    0.06
     Garlic
    0.06
    _HIDE
    0.06
    Act Density 0.000%

    No Known Activations