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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sophomore
    -0.06
     위
    -0.06
    妃
    -0.06
    184
    -0.06
     recommends
    -0.06
    _LD
    -0.06
    Margin
    -0.06
     wel
    -0.06
     проект
    -0.06
    (view
    -0.06
    POSITIVE LOGITS
    energy
    0.08
     copying
    0.07
    Update
    0.07
     update
    0.07
     crane
    0.07
    fill
    0.07
     Australians
    0.07
    <f
    0.07
    olecules
    0.06
     keyboard
    0.06
    Act Density 0.008%

    No Known Activations