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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cay
    -0.07
     nou
    -0.07
    -Ray
    -0.06
     nie
    -0.06
     pst
    -0.06
     计
    -0.06
     Chúa
    -0.06
    ีม
    -0.06
                                                    ↵
    -0.06
    _Button
    -0.06
    POSITIVE LOGITS
     phối
    0.07
    .shell
    0.07
     explosion
    0.07
     versions
    0.06
    gmt
    0.06
    ADMIN
    0.06
    uously
    0.06
    養
    0.06
    	data
    0.06
    parate
    0.06
    Act Density 0.043%

    No Known Activations