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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IsContent
    -0.66
     CreateTagHelper
    -0.57
     الحره
    -0.55
    neos
    -0.52
    Portale
    -0.52
    ệnh
    -0.50
    Autoritní
    -0.49
     Paglinawan
    -0.47
     strick
    -0.47
    <!--[
    -0.46
    POSITIVE LOGITS
     poffe
    0.63
     againſt
    0.57
     favoritas
    0.56
     himſelf
    0.55
     optique
    0.53
     seventh
    0.53
     aisladas
    0.53
     poffible
    0.51
     themſelves
    0.51
    ########.
    0.51
    Act Density 0.001%

    No Known Activations