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

    Neuronpedia

    INDEX
    Explanations

    split

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NoError
    -0.08
    _PROVID
    -0.07
    爱尔
    -0.07
    ')."
    -0.07
    .Stretch
    -0.07
     refuse
    -0.07
    (repository
    -0.07
    Fuse
    -0.07
     censor
    -0.07
    .tasks
    -0.07
    POSITIVE LOGITS
     trimest
    0.07
    .uni
    0.07
    進一步
    0.07
    斤
    0.07
    انية
    0.07
     TL
    0.07
     plotted
    0.07
     Sevilla
    0.07
    _literals
    0.07
    另一边
    0.07
    Act Density 0.013%

    No Known Activations