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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーズ
    -0.07
     directory
    -0.07
    POST
    -0.07
    初期
    -0.07
    ирует
    -0.06
    	Intent
    -0.06
     Emotional
    -0.06
    /cli
    -0.06
    eatures
    -0.06
    eat
    -0.06
    POSITIVE LOGITS
    〛
    0.07
     Sof
    0.07
    ,GL
    0.07
     отнош
    0.07
    .assertIsInstance
    0.07
    گ
    0.07
    xFE
    0.07
    .feedback
    0.07
    ]"
    0.07
    Ｆ
    0.07
    Act Density 0.131%

    No Known Activations