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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Port
    -0.07
     edt
    -0.06
    kud
    -0.06
    �
    -0.06
     kênh
    -0.06
    نوع
    -0.06
     unleashed
    -0.06
     sectors
    -0.06
    .fold
    -0.05
     unsur
    -0.05
    POSITIVE LOGITS
    šli
    0.06
     уточ
    0.06
     Fabric
    0.06
    _normals
    0.06
    \":{\"
    0.06
    _di
    0.06
    ková
    0.06
     χρή
    0.06
    .TestCheck
    0.06
    iş
    0.06
    Act Density 0.003%

    No Known Activations