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

    Neuronpedia

    INDEX
    Explanations

    Initials and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downs
    -0.07
     ¬
    -0.07
     Norse
    -0.07
    難
    -0.07
    Pressed
    -0.06
     donated
    -0.06
    oka
    -0.06
    autom
    -0.06
     Address
    -0.06
    Verb
    -0.06
    POSITIVE LOGITS
     영향
    0.06
     Summers
    0.06
    ै।↵↵
    0.06
    .Edit
    0.06
    _UFunction
    0.06
    /licenses
    0.06
     "";
↵
    0.06
    ")),
    0.06
    toHaveBeenCalledWith
    0.06
     inputData
    0.06
    Act Density 0.305%

    No Known Activations