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

    Neuronpedia

    INDEX
    Explanations

    Can or cannot statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    მ
    -0.07
    泣
    -0.07
     loyal
    -0.07
     spanning
    -0.07
     humid
    -0.06
     lâu
    -0.06
    访问
    -0.06
    Cancellation
    -0.06
     Bij
    -0.06
    ่อง
    -0.06
    POSITIVE LOGITS
     wd
    0.07
    	placeholder
    0.07
     acknowled
    0.07
    _abort
    0.07
    erti
    0.07
     fullPath
    0.06
     qt
    0.06
    뭬
    0.06
    得好
    0.06
    кова
    0.06
    Act Density 0.014%

    No Known Activations