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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Params
    -0.06
     我
    -0.06
     tents
    -0.06
     initializer
    -0.06
     roadmap
    -0.06
     всього
    -0.06
    yp
    -0.06
    _ac
    -0.06
     드립니다
    -0.06
     MSM
    -0.06
    POSITIVE LOGITS
    Metro
    0.07
    FIG
    0.07
    edBy
    0.07
    setw
    0.06
     duke
    0.06
    .Real
    0.06
     negotiate
    0.06
    /exec
    0.06
    coal
    0.06
    Creates
    0.06
    Act Density 0.115%

    No Known Activations