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

    Neuronpedia

    INDEX
    Explanations

    st

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attractive
    -0.08
     depended
    -0.08
    その
    -0.07
     nifty
    -0.07
     forman
    -0.07
     PAT
    -0.07
    Parent
    -0.07
     subi
    -0.07
     uptake
    -0.07
    交流
    -0.07
    POSITIVE LOGITS
     Turkey
    0.09
     ઉપરાંત
    0.09
     vakar
    0.08
    detalle
    0.08
     episódio
    0.08
     Romania
    0.08
     Helvetica
    0.08
     deutscher
    0.08
     �
    0.08
     গুরু
    0.08
    Act Density 0.009%

    No Known Activations