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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mamış
    -0.06
    389
    -0.06
    	entity
    -0.06
    裝
    -0.06
    INAL
    -0.06
     teamwork
    -0.06
    .Stack
    -0.06
    -0.06
     bracelet
    -0.06
                                        ↵
    -0.06
    POSITIVE LOGITS
     Erk
    0.07
    roupon
    0.06
    tos
    0.06
    _images
    0.06
     instagram
    0.06
     shields
    0.06
     ){
↵
    0.06
     aspir
    0.06
    Small
    0.06
    DUCT
    0.06
    Act Density 0.000%

    No Known Activations