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

    Neuronpedia

    INDEX
    Explanations

    disposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .annotation
    -0.07
    idad
    -0.07
    py
    -0.06
    actions
    -0.06
    Compare
    -0.06
     đó
    -0.06
     руч
    -0.06
    ських
    -0.06
    actors
    -0.06
     Heavy
    -0.06
    POSITIVE LOGITS
     بپ
    0.06
     stal
    0.06
     Christina
    0.06
     alice
    0.06
    VERN
    0.06
    вана
    0.06
     finalize
    0.06
    []>
    0.06
     allen
    0.06
    kart
    0.06
    Act Density 0.029%

    No Known Activations