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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setback
    -0.07
     депут
    -0.07
    ors
    -0.07
    ुक
    -0.07
    -ish
    -0.07
     DISPATCH
    -0.07
    єм
    -0.06
    існо
    -0.06
    subclass
    -0.06
    Maybe
    -0.06
    POSITIVE LOGITS
     estilo
    0.06
     citas
    0.06
    witter
    0.06
     columnIndex
    0.06
     plag
    0.06
    /std
    0.06
     wb
    0.05
    ManagerInterface
    0.05
    ños
    0.05
     intervention
    0.05
    Act Density 0.017%

    No Known Activations